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

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

Neuron 3032 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1030195 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.7351. Min Act: -0.0000

Data Index: 929979 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.7194. Min Act: -0.0000

Data Index: 546660 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.7122. Min Act: -0.0000

Data Index: 873537 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6981. Min Act: -0.0000

Data Index: 190302 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6774. Min Act: 0.0000

Data Index: 875130 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1130486 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1220184 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6821. Min Act: -0.0000

Data Index: 668450 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6101. Min Act: -0.0000

Data Index: 926418 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1330506 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6285. Min Act: -0.0000

Data Index: 518649 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1017371 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6042. Min Act: -0.0000

Data Index: 107839 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6211. Min Act: -0.0000

Data Index: 819084 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6166. Min Act: -0.0000

Data Index: 973102 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6165. Min Act: -0.0000

Data Index: 698647 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1100812 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.6367. Min Act: -0.0000

Data Index: 441526 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.7351. Min Range: -0.7351

Max Act: 0.5885. Min Act: -0.0000

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 95