Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0004

Data Index: 798873 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0210. Min Act: -0.0004

Data Index: 943375 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1201718 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0185. Min Act: -0.0004

Data Index: 83019 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0218. Min Act: -0.0004

Data Index: 712360 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0196. Min Act: -0.0004

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0229. Min Act: -0.0004

Data Index: 663107 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0204. Min Act: -0.0004

Data Index: 1288758 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0186. Min Act: -0.0004

Data Index: 998736 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0004

Data Index: 816720 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0201. Min Act: -0.0004

Data Index: 492985 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0207. Min Act: -0.0004

Data Index: 452316 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0193. Min Act: -0.0004

Data Index: 524807 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0223. Min Act: -0.0004

Data Index: 849240 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0199. Min Act: -0.0004

Data Index: 43553 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0190. Min Act: -0.0004

Data Index: 685339 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1083818 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0190. Min Act: -0.0004

Data Index: 650633 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0233. Min Act: -0.0004

Data Index: 56499 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0177. Min Act: -0.0004

Data Index: 1026713 (C4 (Web Text))

Max Activating Token Index: 65