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

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

Neuron 2462 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: 3.5257. Min Range: -3.5257

Max Act: 3.5257. Min Act: -0.0000

Data Index: 502902 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.8363. Min Act: -0.0000

Data Index: 161966 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.8686. Min Act: -0.0000

Data Index: 1213586 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.7295. Min Act: -0.0000

Data Index: 961699 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.4294. Min Act: -0.0000

Data Index: 425462 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.3673. Min Act: -0.0000

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.3205. Min Act: -0.0000

Data Index: 765504 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.1660. Min Act: -0.0000

Data Index: 509399 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.2506. Min Act: -0.0000

Data Index: 476326 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1231218 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.3246. Min Act: -0.0000

Data Index: 641946 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0172. Min Act: -0.0000

Data Index: 792163 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0333. Min Act: -0.0000

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0200. Min Act: -0.0000

Data Index: 650525 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0008. Min Act: -0.0000

Data Index: 59575 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.1797. Min Act: -0.0000

Data Index: 601520 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0708. Min Act: -0.0001

Data Index: 1300324 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0052. Min Act: -0.0000

Data Index: 353470 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.5257. Min Range: -3.5257

Max Act: 2.0004. Min Act: -0.0000

Data Index: 652603 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 3.5257. Min Range: -3.5257

Max Act: 1.8966. Min Act: -0.0000

Data Index: 905527 (C4 (Web Text))

Max Activating Token Index: 384