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

Dataset: Open Web Text

Neuron 1151 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: 4.6089. Min Range: -4.6089

Max Act: 4.6089. Min Act: -0.1700

Data Index: 7062587 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.5320. Min Act: -0.1700

Data Index: 1396775 (Open Web Text)

Max Activating Token Index: 854

Text #2

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.5181. Min Act: -0.1700

Data Index: 2108744 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4743. Min Act: -0.1700

Data Index: 3714722 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4809. Min Act: -0.1700

Data Index: 8402380 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4378. Min Act: -0.1700

Data Index: 2251702 (Open Web Text)

Max Activating Token Index: 923

Text #6

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4561. Min Act: -0.1700

Data Index: 5821023 (Open Web Text)

Max Activating Token Index: 815

Text #7

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4249. Min Act: -0.1700

Data Index: 3500211 (Open Web Text)

Max Activating Token Index: 409

Text #8

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4196. Min Act: -0.1700

Data Index: 429659 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4406. Min Act: -0.1700

Data Index: 5579801 (Open Web Text)

Max Activating Token Index: 463

Text #10

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.3887. Min Act: -0.1700

Data Index: 6944204 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4160. Min Act: -0.1700

Data Index: 6819902 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4256. Min Act: -0.1700

Data Index: 5178413 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4104. Min Act: -0.1700

Data Index: 6585264 (Open Web Text)

Max Activating Token Index: 32

Text #14

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.3958. Min Act: -0.1700

Data Index: 366224 (Open Web Text)

Max Activating Token Index: 922

Text #15

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.3895. Min Act: -0.1700

Data Index: 3224679 (Open Web Text)

Max Activating Token Index: 861

Text #16

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4051. Min Act: -0.1700

Data Index: 335522 (Open Web Text)

Max Activating Token Index: 985

Text #17

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.3771. Min Act: -0.1700

Data Index: 5469763 (Open Web Text)

Max Activating Token Index: 940

Text #18

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4260. Min Act: -0.1700

Data Index: 3748 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 4.6089. Min Range: -4.6089

Max Act: 4.4038. Min Act: -0.1700

Data Index: 1906865 (Open Web Text)

Max Activating Token Index: 229