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

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

Neuron 1635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4941. Min Act: -0.0000

Data Index: 3346 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.5573. Min Act: -0.0000

Data Index: 105456 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4803. Min Act: -0.0000

Data Index: 204030 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4549. Min Act: -0.0000

Data Index: 212364 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4210. Min Act: -0.0000

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3944. Min Act: -0.0000

Data Index: 15585 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4176. Min Act: -0.0000

Data Index: 816365 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1302124 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3896. Min Act: -0.0000

Data Index: 29777 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4319. Min Act: -0.0000

Data Index: 118524 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1324180 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1274033 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3913. Min Act: -0.0000

Data Index: 101519 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1250129 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1249757 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3457. Min Act: -0.0000

Data Index: 987494 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3537. Min Act: -0.0000

Data Index: 866190 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3190. Min Act: -0.0000

Data Index: 849977 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3578. Min Act: -0.0000

Data Index: 172423 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.5573. Min Range: -0.5573

Max Act: 0.3512. Min Act: -0.0000

Data Index: 83388 (C4 (Web Text))

Max Activating Token Index: 264