Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1075 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 564404 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 395834 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 640936 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1106371 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0145. Min Act: -0.0006

Data Index: 190897 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0147. Min Act: -0.0006

Data Index: 333142 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 24596 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0145. Min Act: -0.0006

Data Index: 886401 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 612937 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0144. Min Act: -0.0006

Data Index: 750761 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 607475 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0006

Data Index: 351926 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 280914 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0006

Data Index: 246995 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0006

Data Index: 422076 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0130. Min Act: -0.0006

Data Index: 157980 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 855285 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1049962 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1294416 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0126. Min Act: -0.0006

Data Index: 119718 (C4 (Web Text))

Max Activating Token Index: 623