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

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

Neuron 1633 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: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0006

Data Index: 845805 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1126255 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0169. Min Act: -0.0006

Data Index: 819854 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0167. Min Act: -0.0006

Data Index: 538803 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0166. Min Act: -0.0006

Data Index: 336873 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1332458 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0159. Min Act: -0.0006

Data Index: 71277 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0155. Min Act: -0.0006

Data Index: 22990 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0157. Min Act: -0.0006

Data Index: 81668 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0160. Min Act: -0.0006

Data Index: 129537 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0154. Min Act: -0.0006

Data Index: 893246 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0159. Min Act: -0.0007

Data Index: 196785 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0006

Data Index: 351748 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0006

Data Index: 58288 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0151. Min Act: -0.0006

Data Index: 489594 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0147. Min Act: -0.0006

Data Index: 767081 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1287037 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0006

Data Index: 648419 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0148. Min Act: -0.0006

Data Index: 582241 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1130135 (C4 (Web Text))

Max Activating Token Index: 239