< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 9 in Layer 32

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.7244. Min Act: -0.1700

Data Index: 2060193 (Open Web Text)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.5994. Min Act: -0.1700

Data Index: 6639433 (Open Web Text)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.6306. Min Act: -0.1700

Data Index: 3865410 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.5994. Min Act: -0.1700

Data Index: 3375846 (Open Web Text)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.5056. Min Act: -0.1700

Data Index: 1823655 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.5056. Min Act: -0.1700

Data Index: 4437725 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4744. Min Act: -0.1700

Data Index: 3393026 (Open Web Text)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 1532461 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4431. Min Act: -0.1700

Data Index: 1066064 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4431. Min Act: -0.1700

Data Index: 7266364 (Open Web Text)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 1035587 (Open Web Text)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 5750519 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 2448280 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 7576827 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.3806. Min Act: -0.1700

Data Index: 7833100 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.4119. Min Act: -0.1700

Data Index: 1092356 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.3806. Min Act: -0.1700

Data Index: 3285046 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.3806. Min Act: -0.1700

Data Index: 5074776 (Open Web Text)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.3494. Min Act: -0.1700

Data Index: 317458 (Open Web Text)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.7244. Min Range: -6.7244

Max Act: 6.3494. Min Act: -0.1700

Data Index: 239757 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #19