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

Dataset: Open Web Text

Neuron 135 in Layer 5

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: 5.6842. Min Range: -5.6842

Max Act: 5.6842. Min Act: -0.1700

Data Index: 5278498 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 5.6842. Min Range: -5.6842

Max Act: 5.3221. Min Act: -0.1700

Data Index: 6979609 (Open Web Text)

Max Activating Token Index: 856

Text #2

Max Range: 5.6842. Min Range: -5.6842

Max Act: 5.1199. Min Act: -0.1700

Data Index: 4743760 (Open Web Text)

Max Activating Token Index: 529

Text #3

Max Range: 5.6842. Min Range: -5.6842

Max Act: 5.1014. Min Act: -0.1700

Data Index: 1253595 (Open Web Text)

Max Activating Token Index: 287

Text #4

Max Range: 5.6842. Min Range: -5.6842

Max Act: 5.0142. Min Act: -0.1700

Data Index: 4617959 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9822. Min Act: -0.1700

Data Index: 8562258 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9657. Min Act: -0.1700

Data Index: 1911330 (Open Web Text)

Max Activating Token Index: 855

Text #7

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9708. Min Act: -0.1700

Data Index: 5884321 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9825. Min Act: -0.1700

Data Index: 7072364 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9487. Min Act: -0.1700

Data Index: 3241837 (Open Web Text)

Max Activating Token Index: 891

Text #10

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9264. Min Act: -0.1700

Data Index: 5560979 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9542. Min Act: -0.1700

Data Index: 8355133 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9546. Min Act: -0.1700

Data Index: 2796104 (Open Web Text)

Max Activating Token Index: 74

Text #13

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9252. Min Act: -0.1700

Data Index: 7120081 (Open Web Text)

Max Activating Token Index: 938

Text #14

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.8857. Min Act: -0.1700

Data Index: 920630 (Open Web Text)

Max Activating Token Index: 1018

Text #15

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9146. Min Act: -0.1700

Data Index: 6334570 (Open Web Text)

Max Activating Token Index: 255

Text #16

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.9113. Min Act: -0.1700

Data Index: 5278725 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.8830. Min Act: -0.1700

Data Index: 6382984 (Open Web Text)

Max Activating Token Index: 87

Text #18

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.8613. Min Act: -0.1700

Data Index: 163699 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 5.6842. Min Range: -5.6842

Max Act: 4.8382. Min Act: -0.1700

Data Index: 4476849 (Open Web Text)

Max Activating Token Index: 195