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

Dataset: Open Web Text

Neuron 3058 in Layer 3

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: 4.6157. Min Range: -4.6157

Max Act: 4.6129. Min Act: -0.1700

Data Index: 5505758 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.6157. Min Act: -0.1700

Data Index: 6487977 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5668. Min Act: -0.1700

Data Index: 3549142 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5507. Min Act: -0.1700

Data Index: 8529887 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5531. Min Act: -0.1700

Data Index: 4448593 (Open Web Text)

Max Activating Token Index: 234

Text #5

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.6043. Min Act: -0.1700

Data Index: 2789351 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5732. Min Act: -0.1700

Data Index: 4544923 (Open Web Text)

Max Activating Token Index: 152

Text #7

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5630. Min Act: -0.1700

Data Index: 290398 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4960. Min Act: -0.1700

Data Index: 8494663 (Open Web Text)

Max Activating Token Index: 778

Text #9

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4589. Min Act: -0.1700

Data Index: 4749633 (Open Web Text)

Max Activating Token Index: 577

Text #10

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4940. Min Act: -0.1700

Data Index: 1526767 (Open Web Text)

Max Activating Token Index: 260

Text #11

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4344. Min Act: -0.1700

Data Index: 3201342 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4377. Min Act: -0.1700

Data Index: 8773750 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4210. Min Act: -0.1700

Data Index: 2798804 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5297. Min Act: -0.1700

Data Index: 4800094 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.5355. Min Act: -0.1700

Data Index: 1494594 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4373. Min Act: -0.1700

Data Index: 1224645 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4389. Min Act: -0.1700

Data Index: 2263281 (Open Web Text)

Max Activating Token Index: 90

Text #18

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.4400. Min Act: -0.1700

Data Index: 4949529 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 4.6157. Min Range: -4.6157

Max Act: 4.3538. Min Act: -0.1700

Data Index: 6478679 (Open Web Text)

Max Activating Token Index: 676