Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5479 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0147. Min Act: -0.0002

Data Index: 783115 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1024660 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0144. Min Act: -0.0002

Data Index: 44009 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1026645 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1288032 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0144. Min Act: -0.0002

Data Index: 1106425 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1096037 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0134. Min Act: -0.0002

Data Index: 422819 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1296011 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0143. Min Act: -0.0002

Data Index: 118254 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0130. Min Act: -0.0002

Data Index: 125396 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1534506 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0133. Min Act: -0.0002

Data Index: 208001 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0125. Min Act: -0.0002

Data Index: 842684 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1469352 (Python Code)

Max Activating Token Index: 986

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0126. Min Act: -0.0002

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0123. Min Act: -0.0002

Data Index: 42217 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0124. Min Act: -0.0002

Data Index: 584763 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1546553 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0127. Min Act: -0.0002

Data Index: 166362 (C4 (Web Text))

Max Activating Token Index: 101