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

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

Neuron 1033 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0000

Data Index: 136001 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1355924 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1150707 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1361. Min Act: -0.0000

Data Index: 840335 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1223. Min Act: -0.0000

Data Index: 260851 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1159. Min Act: -0.0000

Data Index: 231004 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1222. Min Act: -0.0000

Data Index: 853565 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.0930. Min Act: -0.0000

Data Index: 432491 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1163. Min Act: -0.0000

Data Index: 572825 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1183. Min Act: -0.0000

Data Index: 973314 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1152719 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1224775 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1167. Min Act: -0.0000

Data Index: 193245 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1148773 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1134. Min Act: -0.0000

Data Index: 333291 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1206. Min Act: -0.0000

Data Index: 444133 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1270. Min Act: -0.0000

Data Index: 13549 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1189. Min Act: -0.0000

Data Index: 916187 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1301574 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1085. Min Act: -0.0000

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 350