< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6344 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.3031. Min Act: -0.1700

Data Index: 7970897 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1468. Min Act: -0.1700

Data Index: 8457232 (Open Web Text)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1468. Min Act: -0.1700

Data Index: 6065678 (Open Web Text)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1156. Min Act: -0.1700

Data Index: 2552926 (Open Web Text)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1156. Min Act: -0.1700

Data Index: 7621678 (Open Web Text)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1156. Min Act: -0.1700

Data Index: 3588822 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.1156. Min Act: -0.1700

Data Index: 8700309 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 347652 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 550480 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 3269705 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 401092 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 5469268 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 1452748 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 8371894 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0843. Min Act: -0.1700

Data Index: 7252535 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0531. Min Act: -0.1700

Data Index: 3815565 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0531. Min Act: -0.1700

Data Index: 6502376 (Open Web Text)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0531. Min Act: -0.1700

Data Index: 4657157 (Open Web Text)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0531. Min Act: -0.1700

Data Index: 6803787 (Open Web Text)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.3031. Min Range: -6.3031

Max Act: 6.0531. Min Act: -0.1700

Data Index: 2222343 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #19