Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1545 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1157011 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0165. Min Act: -0.0006

Data Index: 624909 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0183. Min Act: -0.0006

Data Index: 899944 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0173. Min Act: -0.0006

Data Index: 79064 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0170. Min Act: -0.0006

Data Index: 487385 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1112751 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0162. Min Act: -0.0006

Data Index: 736091 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0147. Min Act: -0.0006

Data Index: 922896 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0151. Min Act: -0.0006

Data Index: 237591 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1083507 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0166. Min Act: -0.0006

Data Index: 502361 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0006

Data Index: 238898 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0154. Min Act: -0.0006

Data Index: 692362 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0154. Min Act: -0.0006

Data Index: 285414 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0006

Data Index: 307215 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0141. Min Act: -0.0006

Data Index: 189306 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0144. Min Act: -0.0006

Data Index: 531662 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0141. Min Act: -0.0006

Data Index: 656653 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0146. Min Act: -0.0006

Data Index: 244077 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0142. Min Act: -0.0006

Data Index: 279638 (C4 (Web Text))

Max Activating Token Index: 314