Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.6164. Min Act: -0.0000

Data Index: 110437 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1274164 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0768. Min Act: -0.0000

Data Index: 608135 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0597. Min Act: -0.0000

Data Index: 607623 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1251986 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0605. Min Act: -0.0000

Data Index: 164630 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0854. Min Act: -0.0000

Data Index: 243538 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9988. Min Act: -0.0000

Data Index: 480897 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9680. Min Act: -0.0000

Data Index: 284704 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1212520 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9603. Min Act: -0.0000

Data Index: 931160 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9690. Min Act: -0.0000

Data Index: 315799 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1155118 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9601. Min Act: -0.0000

Data Index: 446524 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9669. Min Act: -0.0000

Data Index: 791763 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9280. Min Act: -0.0000

Data Index: 473177 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.9163. Min Act: -0.0000

Data Index: 140905 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.6164. Min Range: -1.6164

Max Act: 1.0193. Min Act: -0.0000

Data Index: 901897 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.8345. Min Act: -0.0000

Data Index: 169566 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 1.6164. Min Range: -1.6164

Max Act: 0.8529. Min Act: -0.0000

Data Index: 90007 (C4 (Web Text))

Max Activating Token Index: 812