< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6379 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 11.8059. Min Range: -11.8059

Max Act: 11.8059. Min Act: -0.1700

Data Index: 5866837 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.8059. Min Act: -0.1700

Data Index: 8366585 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.5559. Min Act: -0.1700

Data Index: 2810075 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.5559. Min Act: -0.1700

Data Index: 6469421 (Open Web Text)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.4934. Min Act: -0.1700

Data Index: 8640416 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.4309. Min Act: -0.1700

Data Index: 6469420 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.4309. Min Act: -0.1700

Data Index: 746573 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.3684. Min Act: -0.1700

Data Index: 1490505 (Open Web Text)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.2434. Min Act: -0.1700

Data Index: 3803512 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.2434. Min Act: -0.1700

Data Index: 2138264 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.0559. Min Act: -0.1700

Data Index: 3170241 (Open Web Text)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.0559. Min Act: -0.1700

Data Index: 235988 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 11.8059. Min Range: -11.8059

Max Act: 10.0559. Min Act: -0.1700

Data Index: 3242374 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.9934. Min Act: -0.1700

Data Index: 6059676 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.9934. Min Act: -0.1700

Data Index: 4461197 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.9934. Min Act: -0.1700

Data Index: 7767269 (Open Web Text)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.8684. Min Act: -0.1700

Data Index: 8001976 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.9309. Min Act: -0.1700

Data Index: 4708409 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.8684. Min Act: -0.1700

Data Index: 3857062 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 11.8059. Min Range: -11.8059

Max Act: 9.8684. Min Act: -0.1700

Data Index: 2584164 (Open Web Text)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #19