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

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

Neuron 4096 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: 0.1327. Min Range: -0.1327

Max Act: 0.1222. Min Act: -0.0002

Data Index: 767809 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1327. Min Act: -0.0002

Data Index: 68715 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1004950 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1107. Min Act: -0.0002

Data Index: 888289 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1178. Min Act: -0.0002

Data Index: 833954 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1172. Min Act: -0.0002

Data Index: 683943 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1194. Min Act: -0.0002

Data Index: 211819 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1150. Min Act: -0.0002

Data Index: 449814 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1025233 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1132. Min Act: -0.0002

Data Index: 67413 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1065431 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1235. Min Act: -0.0002

Data Index: 297925 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1207733 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1294497 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1063. Min Act: -0.0002

Data Index: 522249 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1172. Min Act: -0.0002

Data Index: 551398 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1170. Min Act: -0.0002

Data Index: 425575 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1118. Min Act: -0.0002

Data Index: 71490 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1156. Min Act: -0.0002

Data Index: 988001 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.1327. Min Range: -0.1327

Max Act: 0.1068. Min Act: -0.0002

Data Index: 425245 (C4 (Web Text))

Max Activating Token Index: 932