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

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

Neuron 233 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1264545 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0177. Min Act: -0.0003

Data Index: 163068 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0164. Min Act: -0.0003

Data Index: 674355 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0165. Min Act: -0.0003

Data Index: 331988 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0151. Min Act: -0.0003

Data Index: 269726 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0148. Min Act: -0.0003

Data Index: 939032 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0146. Min Act: -0.0002

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1342994 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0141. Min Act: -0.0003

Data Index: 289530 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0143. Min Act: -0.0003

Data Index: 106125 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0136. Min Act: -0.0003

Data Index: 935232 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0133. Min Act: -0.0003

Data Index: 969003 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0133. Min Act: -0.0003

Data Index: 589086 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0136. Min Act: -0.0003

Data Index: 871735 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1146947 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1301276 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0131. Min Act: -0.0003

Data Index: 89987 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0129. Min Act: -0.0003

Data Index: 778615 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0130. Min Act: -0.0003

Data Index: 729231 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1186827 (C4 (Web Text))

Max Activating Token Index: 628