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

Dataset: Open Web Text

Neuron 437 in Layer 2

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: 4.2385. Min Range: -4.2385

Max Act: 4.2385. Min Act: -0.1700

Data Index: 8143699 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1509. Min Act: -0.1700

Data Index: 5957348 (Open Web Text)

Max Activating Token Index: 780

Text #2

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1346. Min Act: -0.1700

Data Index: 25707 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1286. Min Act: -0.1700

Data Index: 2939498 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1308. Min Act: -0.1700

Data Index: 7272250 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1426. Min Act: -0.1700

Data Index: 159342 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1419. Min Act: -0.1700

Data Index: 6858328 (Open Web Text)

Max Activating Token Index: 411

Text #7

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1187. Min Act: -0.1700

Data Index: 3451241 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1164. Min Act: -0.1700

Data Index: 6652595 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1215. Min Act: -0.1700

Data Index: 5857477 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1241. Min Act: -0.1700

Data Index: 5699179 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1035. Min Act: -0.1700

Data Index: 1815651 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1088. Min Act: -0.1700

Data Index: 6004473 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1043. Min Act: -0.1700

Data Index: 462313 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.0871. Min Act: -0.1700

Data Index: 5007748 (Open Web Text)

Max Activating Token Index: 185

Text #15

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1036. Min Act: -0.1700

Data Index: 4853814 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.0896. Min Act: -0.1700

Data Index: 4474463 (Open Web Text)

Max Activating Token Index: 154

Text #17

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.0807. Min Act: -0.1700

Data Index: 3360677 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.1037. Min Act: -0.1700

Data Index: 612070 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 4.2385. Min Range: -4.2385

Max Act: 4.0851. Min Act: -0.1700

Data Index: 787070 (Open Web Text)

Max Activating Token Index: 435