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

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

Neuron 3070 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1205. Min Range: -1.1205

Max Act: 1.1205. Min Act: -0.0000

Data Index: 821825 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.1205. Min Range: -1.1205

Max Act: 1.1120. Min Act: -0.0000

Data Index: 636108 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.8214. Min Act: -0.0000

Data Index: 214625 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1104468 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1121496 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.7090. Min Act: -0.0000

Data Index: 976022 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.7428. Min Act: -0.0000

Data Index: 198202 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1068363 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1097571 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6386. Min Act: -0.0000

Data Index: 781244 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6152. Min Act: -0.0000

Data Index: 768915 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1211732 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1256880 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1033028 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.5688. Min Act: -0.0000

Data Index: 470548 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6013. Min Act: -0.0000

Data Index: 262284 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1050006 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.6145. Min Act: -0.0000

Data Index: 716448 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.5681. Min Act: -0.0000

Data Index: 183853 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.1205. Min Range: -1.1205

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1226562 (C4 (Web Text))

Max Activating Token Index: 756