Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1158 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.6345. Min Act: -0.0000

Data Index: 67989 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.4076. Min Act: -0.0000

Data Index: 881033 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.4627. Min Act: -0.0000

Data Index: 769172 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3794. Min Act: -0.0000

Data Index: 457657 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3698. Min Act: -0.0000

Data Index: 752379 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3444. Min Act: -0.0000

Data Index: 683761 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1179849 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1309615 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3664. Min Act: -0.0000

Data Index: 682257 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1153160 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1624878 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1120381 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3185. Min Act: -0.0000

Data Index: 373807 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1643823 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.2787. Min Act: -0.0000

Data Index: 134719 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.2956. Min Act: -0.0000

Data Index: 825907 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.2828. Min Act: -0.0000

Data Index: 164799 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1185144 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1616534 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 0.6345. Min Range: -0.6345

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1010270 (C4 (Web Text))

Max Activating Token Index: 982