Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7187. Min Act: -0.1700

Data Index: 989744 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7324. Min Act: -0.1700

Data Index: 8280217 (Open Web Text)

Max Activating Token Index: 965

Text #2

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6883. Min Act: -0.1700

Data Index: 966458 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6314. Min Act: -0.1700

Data Index: 4698398 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6293. Min Act: -0.1700

Data Index: 3570253 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1988080 (Open Web Text)

Max Activating Token Index: 349

Text #6

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6301. Min Act: -0.1700

Data Index: 6478586 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6113. Min Act: -0.1700

Data Index: 3101789 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5762. Min Act: -0.1700

Data Index: 892346 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5788. Min Act: -0.1700

Data Index: 5958579 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5809. Min Act: -0.1700

Data Index: 5750495 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5893. Min Act: -0.1700

Data Index: 3472384 (Open Web Text)

Max Activating Token Index: 586

Text #12

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5536. Min Act: -0.1700

Data Index: 5362407 (Open Web Text)

Max Activating Token Index: 902

Text #13

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5587. Min Act: -0.1700

Data Index: 2403733 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5693. Min Act: -0.1700

Data Index: 64813 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5519. Min Act: -0.1700

Data Index: 2072994 (Open Web Text)

Max Activating Token Index: 359

Text #16

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5755. Min Act: -0.1700

Data Index: 2510093 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5346. Min Act: -0.1700

Data Index: 2823492 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5514. Min Act: -0.1700

Data Index: 5160581 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5152. Min Act: -0.1700

Data Index: 1032864 (Open Web Text)

Max Activating Token Index: 515