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

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

Neuron 1940 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1218515 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0238. Min Act: -0.0002

Data Index: 608350 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0209. Min Act: -0.0002

Data Index: 540302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0198. Min Act: -0.0002

Data Index: 465606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0203. Min Act: -0.0002

Data Index: 644005 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1065442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0186. Min Act: -0.0002

Data Index: 190922 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0154. Min Act: -0.0002

Data Index: 769583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0173. Min Act: -0.0002

Data Index: 729607 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1124003 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0167. Min Act: -0.0002

Data Index: 612471 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0163. Min Act: -0.0002

Data Index: 575115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1336109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1204670 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1024610 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1584607 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0137. Min Act: -0.0002

Data Index: 907118 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0150. Min Act: -0.0002

Data Index: 319795 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0160. Min Act: -0.0002

Data Index: 1125496 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0289. Min Range: -0.0289

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1582999 (Python Code)

Max Activating Token Index: 450