< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 50 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.8522. Min Act: -0.1700

Data Index: 1175534 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.7897. Min Act: -0.1700

Data Index: 1591639 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.3522. Min Act: -0.1700

Data Index: 6899982 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.3522. Min Act: -0.1700

Data Index: 2419285 (Open Web Text)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.2272. Min Act: -0.1700

Data Index: 4624642 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.2272. Min Act: -0.1700

Data Index: 519401 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.2272. Min Act: -0.1700

Data Index: 3477186 (Open Web Text)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.2272. Min Act: -0.1700

Data Index: 2408972 (Open Web Text)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1647. Min Act: -0.1700

Data Index: 2704396 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1647. Min Act: -0.1700

Data Index: 2270546 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1022. Min Act: -0.1700

Data Index: 221536 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1022. Min Act: -0.1700

Data Index: 5381648 (Open Web Text)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1647. Min Act: -0.1700

Data Index: 1041274 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1022. Min Act: -0.1700

Data Index: 8690991 (Open Web Text)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1022. Min Act: -0.1700

Data Index: 1759506 (Open Web Text)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.1022. Min Act: -0.1700

Data Index: 2840504 (Open Web Text)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.0397. Min Act: -0.1700

Data Index: 1570083 (Open Web Text)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.0397. Min Act: -0.1700

Data Index: 4572018 (Open Web Text)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.0397. Min Act: -0.1700

Data Index: 7514851 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.8522. Min Range: -8.8522

Max Act: 8.0397. Min Act: -0.1700

Data Index: 8298492 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #19