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

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

Neuron 1292 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0245. Min Act: -0.0002

Data Index: 566248 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0173. Min Act: -0.0002

Data Index: 408582 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0154. Min Act: -0.0002

Data Index: 222009 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0167. Min Act: -0.0002

Data Index: 296381 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0168. Min Act: -0.0002

Data Index: 596064 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1068131 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1093144 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0169. Min Act: -0.0002

Data Index: 510329 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0151. Min Act: -0.0002

Data Index: 871034 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0157. Min Act: -0.0002

Data Index: 473946 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0165. Min Act: -0.0002

Data Index: 825517 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0145. Min Act: -0.0002

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0150. Min Act: -0.0002

Data Index: 935959 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0165. Min Act: -0.0002

Data Index: 379895 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0147. Min Act: -0.0001

Data Index: 770044 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0143. Min Act: -0.0002

Data Index: 277246 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1092832 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0141. Min Act: -0.0002

Data Index: 480909 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0135. Min Act: -0.0002

Data Index: 544464 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.0245. Min Range: -0.0245

Max Act: 0.0137. Min Act: -0.0002

Data Index: 273766 (C4 (Web Text))

Max Activating Token Index: 362