Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 282 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0005

Data Index: 218907 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1188. Min Act: -0.0005

Data Index: 584309 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1240. Min Act: -0.0005

Data Index: 544299 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1189. Min Act: -0.0005

Data Index: 985934 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1286. Min Act: -0.0005

Data Index: 602123 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1226. Min Act: -0.0005

Data Index: 271333 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1255. Min Act: -0.0005

Data Index: 348380 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1310. Min Act: -0.0005

Data Index: 5234 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1181. Min Act: -0.0005

Data Index: 584476 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1137. Min Act: -0.0005

Data Index: 157408 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1159. Min Act: -0.0005

Data Index: 710280 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1006. Min Act: -0.0005

Data Index: 366992 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1163. Min Act: -0.0005

Data Index: 74789 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1158. Min Act: -0.0005

Data Index: 478604 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1136. Min Act: -0.0005

Data Index: 1041894 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1101. Min Act: -0.0005

Data Index: 319086 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1143. Min Act: -0.0005

Data Index: 558647 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1136. Min Act: -0.0005

Data Index: 818660 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1041. Min Act: -0.0005

Data Index: 282239 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1087. Min Act: -0.0005

Data Index: 1033531 (C4 (Web Text))

Max Activating Token Index: 34