Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3394 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0002

Data Index: 865666 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0202. Min Act: -0.0002

Data Index: 207367 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0201. Min Act: -0.0002

Data Index: 829028 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0199. Min Act: -0.0002

Data Index: 745623 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0196. Min Act: -0.0002

Data Index: 882094 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0192. Min Act: -0.0002

Data Index: 29117 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0192. Min Act: -0.0002

Data Index: 619329 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0187. Min Act: -0.0002

Data Index: 661913 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0002

Data Index: 350106 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0002

Data Index: 142704 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0002

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0002

Data Index: 406562 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0002

Data Index: 800566 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0185. Min Act: -0.0002

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0185. Min Act: -0.0002

Data Index: 818831 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0185. Min Act: -0.0002

Data Index: 572846 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0002

Data Index: 640453 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0181. Min Act: -0.0002

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0002

Data Index: 703130 (C4 (Web Text))

Max Activating Token Index: 606