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

Dataset: Open Web Text

Neuron 1313 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: 1.8102. Min Range: -1.8102

Max Act: 1.8102. Min Act: -0.1700

Data Index: 3257768 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7765. Min Act: -0.1700

Data Index: 2266207 (Open Web Text)

Max Activating Token Index: 588

Text #2

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7947. Min Act: -0.1700

Data Index: 5824160 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7535. Min Act: -0.1700

Data Index: 1359314 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7459. Min Act: -0.1700

Data Index: 3940441 (Open Web Text)

Max Activating Token Index: 732

Text #5

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7498. Min Act: -0.1700

Data Index: 2876512 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7424. Min Act: -0.1700

Data Index: 4895850 (Open Web Text)

Max Activating Token Index: 39

Text #7

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7294. Min Act: -0.1700

Data Index: 2266211 (Open Web Text)

Max Activating Token Index: 57

Text #8

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7341. Min Act: -0.1700

Data Index: 2749066 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7392. Min Act: -0.1700

Data Index: 6020229 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7181. Min Act: -0.1700

Data Index: 4485169 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.7122. Min Act: -0.1700

Data Index: 5523139 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6828. Min Act: -0.1700

Data Index: 3209848 (Open Web Text)

Max Activating Token Index: 457

Text #13

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6901. Min Act: -0.1700

Data Index: 4262086 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6841. Min Act: -0.1700

Data Index: 2953720 (Open Web Text)

Max Activating Token Index: 758

Text #15

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6838. Min Act: -0.1700

Data Index: 7049898 (Open Web Text)

Max Activating Token Index: 499

Text #16

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6916. Min Act: -0.1700

Data Index: 1870340 (Open Web Text)

Max Activating Token Index: 578

Text #17

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6883. Min Act: -0.1700

Data Index: 4165986 (Open Web Text)

Max Activating Token Index: 156

Text #18

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6812. Min Act: -0.1700

Data Index: 2821506 (Open Web Text)

Max Activating Token Index: 547

Text #19

Max Range: 1.8102. Min Range: -1.8102

Max Act: 1.6840. Min Act: -0.1700

Data Index: 5140611 (Open Web Text)

Max Activating Token Index: 372