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

Dataset: Open Web Text

Neuron 1597 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: 1.0148. Min Range: -1.0148

Max Act: 1.0148. Min Act: -0.1699

Data Index: 2505999 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9791. Min Act: -0.1450

Data Index: 2179299 (Open Web Text)

Max Activating Token Index: 494

Text #2

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9778. Min Act: -0.1690

Data Index: 2625165 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9724. Min Act: -0.1351

Data Index: 6127743 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9320. Min Act: -0.1698

Data Index: 2091421 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9514. Min Act: -0.1677

Data Index: 283873 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9527. Min Act: -0.1696

Data Index: 3175591 (Open Web Text)

Max Activating Token Index: 167

Text #7

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9594. Min Act: -0.1351

Data Index: 6831578 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9283. Min Act: -0.1696

Data Index: 7659598 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9523. Min Act: -0.1700

Data Index: 5138525 (Open Web Text)

Max Activating Token Index: 248

Text #10

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9395. Min Act: -0.1696

Data Index: 7672794 (Open Web Text)

Max Activating Token Index: 625

Text #11

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9434. Min Act: -0.1700

Data Index: 8250812 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9329. Min Act: -0.1700

Data Index: 7179885 (Open Web Text)

Max Activating Token Index: 111

Text #13

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9251. Min Act: -0.1700

Data Index: 2492324 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9313. Min Act: -0.1699

Data Index: 1928458 (Open Web Text)

Max Activating Token Index: 810

Text #15

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9281. Min Act: -0.1698

Data Index: 3997247 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9400. Min Act: -0.1696

Data Index: 5800943 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9370. Min Act: -0.1692

Data Index: 2904148 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9373. Min Act: -0.1700

Data Index: 2129600 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 1.0148. Min Range: -1.0148

Max Act: 0.9300. Min Act: -0.1700

Data Index: 2570937 (Open Web Text)

Max Activating Token Index: 365