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

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

Neuron 1615 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0005

Data Index: 208392 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0193. Min Act: -0.0005

Data Index: 363757 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0190. Min Act: -0.0005

Data Index: 183378 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0192. Min Act: -0.0005

Data Index: 861206 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0188. Min Act: -0.0005

Data Index: 906803 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0188. Min Act: -0.0005

Data Index: 603739 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0190. Min Act: -0.0005

Data Index: 1091736 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0006

Data Index: 129577 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1277736 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0005

Data Index: 422067 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1194512 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0182. Min Act: -0.0005

Data Index: 77204 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0005

Data Index: 941261 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0179. Min Act: -0.0005

Data Index: 198704 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0173. Min Act: -0.0005

Data Index: 289848 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0177. Min Act: -0.0005

Data Index: 256715 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0177. Min Act: -0.0006

Data Index: 371713 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0172. Min Act: -0.0005

Data Index: 1060069 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0176. Min Act: -0.0005

Data Index: 688090 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1174039 (C4 (Web Text))

Max Activating Token Index: 867