Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4064 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0003

Data Index: 267904 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0181. Min Act: -0.0003

Data Index: 359791 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0184. Min Act: -0.0003

Data Index: 91957 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0187. Min Act: -0.0003

Data Index: 884505 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0179. Min Act: -0.0004

Data Index: 906050 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1234920 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0170. Min Act: -0.0003

Data Index: 809229 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0003

Data Index: 546488 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1181523 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0165. Min Act: -0.0003

Data Index: 398331 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0168. Min Act: -0.0003

Data Index: 865955 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1173835 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1095860 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1212633 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0159. Min Act: -0.0003

Data Index: 957862 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1129841 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0165. Min Act: -0.0003

Data Index: 587609 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0160. Min Act: -0.0003

Data Index: 113945 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0164. Min Act: -0.0003

Data Index: 382289 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0163. Min Act: -0.0003

Data Index: 729587 (C4 (Web Text))

Max Activating Token Index: 24