Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0003

Data Index: 979519 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0003

Data Index: 444784 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0003

Data Index: 57287 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0246. Min Act: -0.0003

Data Index: 630679 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0227. Min Act: -0.0003

Data Index: 254591 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0249. Min Act: -0.0003

Data Index: 896504 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0003

Data Index: 821643 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1233122 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0220. Min Act: -0.0003

Data Index: 195993 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0218. Min Act: -0.0003

Data Index: 739402 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0226. Min Act: -0.0003

Data Index: 754456 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0234. Min Act: -0.0003

Data Index: 316625 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0003

Data Index: 118028 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1267201 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0214. Min Act: -0.0003

Data Index: 25041 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0234. Min Act: -0.0003

Data Index: 982148 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0205. Min Act: -0.0003

Data Index: 160073 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0227. Min Act: -0.0003

Data Index: 662114 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1339909 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0212. Min Act: -0.0003

Data Index: 293669 (C4 (Web Text))

Max Activating Token Index: 1009