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

Dataset: Open Web Text

Neuron 2556 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: 1.8028. Min Range: -1.8028

Max Act: 1.8028. Min Act: -0.1700

Data Index: 5344557 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7458. Min Act: -0.1697

Data Index: 3405384 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7452. Min Act: -0.1700

Data Index: 518367 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7496. Min Act: -0.1700

Data Index: 2191014 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7284. Min Act: -0.1699

Data Index: 5760327 (Open Web Text)

Max Activating Token Index: 507

Text #5

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7345. Min Act: -0.1700

Data Index: 2333580 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7281. Min Act: -0.1700

Data Index: 1003086 (Open Web Text)

Max Activating Token Index: 465

Text #7

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7260. Min Act: -0.1699

Data Index: 5361971 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7216. Min Act: -0.1700

Data Index: 4828983 (Open Web Text)

Max Activating Token Index: 804

Text #9

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7339. Min Act: -0.1700

Data Index: 6194235 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7256. Min Act: -0.1700

Data Index: 7652721 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7176. Min Act: -0.1700

Data Index: 8492972 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7129. Min Act: -0.1699

Data Index: 530281 (Open Web Text)

Max Activating Token Index: 639

Text #13

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7136. Min Act: -0.1700

Data Index: 3771886 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7198. Min Act: -0.1700

Data Index: 4667871 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7144. Min Act: -0.1700

Data Index: 5553898 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7074. Min Act: -0.1700

Data Index: 4205140 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7122. Min Act: -0.1700

Data Index: 2204660 (Open Web Text)

Max Activating Token Index: 286

Text #18

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7121. Min Act: -0.1699

Data Index: 1510054 (Open Web Text)

Max Activating Token Index: 295

Text #19

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.7114. Min Act: -0.1700

Data Index: 7469158 (Open Web Text)

Max Activating Token Index: 398