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

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

Neuron 2295 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0002

Data Index: 678227 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0199. Min Act: -0.0002

Data Index: 869590 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0181. Min Act: -0.0002

Data Index: 716386 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1645744 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0173. Min Act: -0.0003

Data Index: 731226 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1276375 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0162. Min Act: -0.0003

Data Index: 67366 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0159. Min Act: -0.0002

Data Index: 906979 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0159. Min Act: -0.0002

Data Index: 882320 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0159. Min Act: -0.0003

Data Index: 449460 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0159. Min Act: -0.0002

Data Index: 313651 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0159. Min Act: -0.0003

Data Index: 924446 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0154. Min Act: -0.0002

Data Index: 588699 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0154. Min Act: -0.0002

Data Index: 660596 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0151. Min Act: -0.0002

Data Index: 883469 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0153. Min Act: -0.0002

Data Index: 582604 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0152. Min Act: -0.0003

Data Index: 148898 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0149. Min Act: -0.0003

Data Index: 90292 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1577631 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0152. Min Act: -0.0003

Data Index: 286452 (C4 (Web Text))

Max Activating Token Index: 2