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

Dataset: Open Web Text

Neuron 3033 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: 5.1067. Min Range: -5.1067

Max Act: 5.1067. Min Act: -0.1700

Data Index: 7849332 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.9632. Min Act: -0.1700

Data Index: 5901466 (Open Web Text)

Max Activating Token Index: 842

Text #2

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.9064. Min Act: -0.1700

Data Index: 7539504 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.8343. Min Act: -0.1700

Data Index: 4026415 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.8159. Min Act: -0.1700

Data Index: 3754936 (Open Web Text)

Max Activating Token Index: 394

Text #5

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.8149. Min Act: -0.1700

Data Index: 1348906 (Open Web Text)

Max Activating Token Index: 464

Text #6

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7800. Min Act: -0.1700

Data Index: 2916499 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7855. Min Act: -0.1700

Data Index: 7959197 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7376. Min Act: -0.1700

Data Index: 7114733 (Open Web Text)

Max Activating Token Index: 785

Text #9

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7597. Min Act: -0.1700

Data Index: 7106718 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7567. Min Act: -0.1700

Data Index: 4838626 (Open Web Text)

Max Activating Token Index: 647

Text #11

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7244. Min Act: -0.1700

Data Index: 5713653 (Open Web Text)

Max Activating Token Index: 113

Text #12

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7142. Min Act: -0.1700

Data Index: 5762593 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.6758. Min Act: -0.1700

Data Index: 3933282 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7014. Min Act: -0.1700

Data Index: 507512 (Open Web Text)

Max Activating Token Index: 239

Text #15

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.7352. Min Act: -0.1700

Data Index: 7100745 (Open Web Text)

Max Activating Token Index: 588

Text #16

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.6989. Min Act: -0.1700

Data Index: 7757889 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.6828. Min Act: -0.1700

Data Index: 4201167 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.6127. Min Act: -0.1700

Data Index: 1580937 (Open Web Text)

Max Activating Token Index: 926

Text #19

Max Range: 5.1067. Min Range: -5.1067

Max Act: 4.6389. Min Act: -0.1700

Data Index: 2811228 (Open Web Text)

Max Activating Token Index: 56