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

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

Neuron 185 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: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0002

Data Index: 413888 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1272804 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1346407 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0002

Data Index: 159936 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1529579 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0002

Data Index: 60629 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0002

Data Index: 16981 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1519553 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0151. Min Act: -0.0002

Data Index: 438524 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0002

Data Index: 443702 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0002

Data Index: 17077 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1460278 (Python Code)

Max Activating Token Index: 396

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 58480 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 248271 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0002

Data Index: 221056 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0143. Min Act: -0.0002

Data Index: 34150 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1044487 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0142. Min Act: -0.0002

Data Index: 252508 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1317482 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0141. Min Act: -0.0002

Data Index: 426006 (C4 (Web Text))

Max Activating Token Index: 322