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

Dataset: Open Web Text

Neuron 1189 in Layer 4

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: 4.9847. Min Range: -4.9847

Max Act: 4.9847. Min Act: -0.1700

Data Index: 6696304 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.9169. Min Act: -0.1700

Data Index: 4213079 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.8948. Min Act: -0.1700

Data Index: 2875788 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.8754. Min Act: -0.1700

Data Index: 8454146 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.8570. Min Act: -0.1700

Data Index: 7293770 (Open Web Text)

Max Activating Token Index: 405

Text #5

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.8805. Min Act: -0.1700

Data Index: 6000540 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7995. Min Act: -0.1700

Data Index: 5428478 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7716. Min Act: -0.1700

Data Index: 1769724 (Open Web Text)

Max Activating Token Index: 341

Text #8

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7712. Min Act: -0.1700

Data Index: 4125708 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7412. Min Act: -0.1700

Data Index: 109582 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7355. Min Act: -0.1700

Data Index: 4276057 (Open Web Text)

Max Activating Token Index: 599

Text #11

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7041. Min Act: -0.1700

Data Index: 3443240 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.7177. Min Act: -0.1700

Data Index: 5737893 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6454. Min Act: -0.1700

Data Index: 4345665 (Open Web Text)

Max Activating Token Index: 747

Text #14

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6141. Min Act: -0.1700

Data Index: 363168 (Open Web Text)

Max Activating Token Index: 367

Text #15

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6396. Min Act: -0.1700

Data Index: 3019646 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6940. Min Act: -0.1700

Data Index: 1699935 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.5609. Min Act: -0.1700

Data Index: 2843989 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6095. Min Act: -0.1700

Data Index: 2860187 (Open Web Text)

Max Activating Token Index: 921

Text #19

Max Range: 4.9847. Min Range: -4.9847

Max Act: 4.6100. Min Act: -0.1700

Data Index: 5123395 (Open Web Text)

Max Activating Token Index: 204