Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0001

Data Index: 662968 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1087871 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0170. Min Act: -0.0001

Data Index: 341992 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1052059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0167. Min Act: -0.0001

Data Index: 551636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0160. Min Act: -0.0001

Data Index: 64397 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0163. Min Act: -0.0001

Data Index: 316113 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1022063 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1083877 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0155. Min Act: -0.0001

Data Index: 198819 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0154. Min Act: -0.0001

Data Index: 820058 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0151. Min Act: -0.0001

Data Index: 203571 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0150. Min Act: -0.0001

Data Index: 108105 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1124336 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1139757 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0001

Data Index: 1217955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0147. Min Act: -0.0001

Data Index: 440475 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0147. Min Act: -0.0001

Data Index: 213347 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0001

Data Index: 303057 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1157311 (C4 (Web Text))

Max Activating Token Index: 1023