Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 714 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1134677 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0239. Min Act: -0.0006

Data Index: 68467 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0006

Data Index: 187886 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0215. Min Act: -0.0006

Data Index: 398529 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0191. Min Act: -0.0006

Data Index: 615871 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0170. Min Act: -0.0006

Data Index: 717087 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1217154 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0193. Min Act: -0.0006

Data Index: 371118 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1183460 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1350987 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0209. Min Act: -0.0006

Data Index: 611249 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0169. Min Act: -0.0006

Data Index: 618339 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0006

Data Index: 14510 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0221. Min Act: -0.0006

Data Index: 102557 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0006

Data Index: 303091 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0219. Min Act: -0.0006

Data Index: 419117 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0228. Min Act: -0.0006

Data Index: 569321 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0204. Min Act: -0.0006

Data Index: 731161 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0215. Min Act: -0.0006

Data Index: 836104 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.0260. Min Range: -0.0260

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1055708 (C4 (Web Text))

Max Activating Token Index: 548