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

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

Neuron 66 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3762. Min Act: -0.0000

Data Index: 7241 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.4254. Min Act: -0.0000

Data Index: 1204325 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2507. Min Act: -0.0000

Data Index: 81564 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2170. Min Act: -0.0000

Data Index: 1053994 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3158. Min Act: -0.0000

Data Index: 82156 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2524. Min Act: -0.0000

Data Index: 186681 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3656. Min Act: -0.0000

Data Index: 141534 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2765. Min Act: -0.0000

Data Index: 970408 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1164801 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3445. Min Act: -0.0001

Data Index: 114379 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.3201. Min Act: -0.0001

Data Index: 1135851 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2245. Min Act: -0.0000

Data Index: 516840 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.2742. Min Act: -0.0000

Data Index: 65056 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.1372. Min Act: -0.0001

Data Index: 733417 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.1498. Min Act: -0.0000

Data Index: 670210 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.0967. Min Act: -0.0000

Data Index: 987611 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.1449. Min Act: -0.0001

Data Index: 143195 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.1102. Min Act: -0.0000

Data Index: 702223 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 2.4254. Min Range: -2.4254

Max Act: 1.9511. Min Act: -0.0000

Data Index: 794753 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.4254. Min Range: -2.4254

Max Act: 2.0306. Min Act: -0.0000

Data Index: 519009 (C4 (Web Text))

Max Activating Token Index: 961