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

Dataset: Open Web Text

Neuron 1160 in Layer 1

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: 1.9112. Min Range: -1.9112

Max Act: 1.9112. Min Act: -0.1699

Data Index: 3731131 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8859. Min Act: -0.1699

Data Index: 7505428 (Open Web Text)

Max Activating Token Index: 163

Text #2

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8649. Min Act: -0.1700

Data Index: 4824883 (Open Web Text)

Max Activating Token Index: 451

Text #3

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8406. Min Act: -0.1700

Data Index: 2457163 (Open Web Text)

Max Activating Token Index: 129

Text #4

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8480. Min Act: -0.1700

Data Index: 3241397 (Open Web Text)

Max Activating Token Index: 354

Text #5

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8509. Min Act: -0.1700

Data Index: 7821234 (Open Web Text)

Max Activating Token Index: 326

Text #6

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8467. Min Act: -0.1700

Data Index: 2852605 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8437. Min Act: -0.1700

Data Index: 7598345 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8406. Min Act: -0.1700

Data Index: 1100270 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8372. Min Act: -0.1700

Data Index: 5036948 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8328. Min Act: -0.1700

Data Index: 6421068 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8282. Min Act: -0.1700

Data Index: 5476604 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8329. Min Act: -0.1700

Data Index: 6911034 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8268. Min Act: -0.1700

Data Index: 8100023 (Open Web Text)

Max Activating Token Index: 275

Text #14

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8348. Min Act: -0.1700

Data Index: 6275474 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8384. Min Act: -0.1699

Data Index: 2400506 (Open Web Text)

Max Activating Token Index: 776

Text #16

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8218. Min Act: -0.1700

Data Index: 822297 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8207. Min Act: -0.1700

Data Index: 5159923 (Open Web Text)

Max Activating Token Index: 489

Text #18

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8194. Min Act: -0.1698

Data Index: 5791656 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 1.9112. Min Range: -1.9112

Max Act: 1.8244. Min Act: -0.1700

Data Index: 5988665 (Open Web Text)

Max Activating Token Index: 267