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

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

Neuron 4170 in Layer 1

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: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1093572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0199. Min Act: -0.0002

Data Index: 421768 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1001074 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0187. Min Act: -0.0002

Data Index: 125015 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0177. Min Act: -0.0002

Data Index: 619540 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1062936 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0164. Min Act: -0.0003

Data Index: 816392 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1180926 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0156. Min Act: -0.0002

Data Index: 651738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1206084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0154. Min Act: -0.0002

Data Index: 202992 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0156. Min Act: -0.0002

Data Index: 198736 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1126036 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1017031 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0154. Min Act: -0.0002

Data Index: 665619 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0149. Min Act: -0.0002

Data Index: 498030 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0151. Min Act: -0.0003

Data Index: 163998 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0145. Min Act: -0.0002

Data Index: 920736 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0148. Min Act: -0.0002

Data Index: 405938 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0145. Min Act: -0.0002

Data Index: 848907 (C4 (Web Text))

Max Activating Token Index: 45