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

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

Neuron 2142 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0001

Data Index: 528155 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1270. Min Act: -0.0001

Data Index: 876277 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1299225 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1195. Min Act: -0.0001

Data Index: 679633 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1176814 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1197510 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1200. Min Act: -0.0001

Data Index: 127924 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1264. Min Act: -0.0000

Data Index: 887528 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1264. Min Act: -0.0001

Data Index: 50225 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1238. Min Act: -0.0001

Data Index: 731562 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1090. Min Act: -0.0001

Data Index: 274042 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1019993 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1086. Min Act: -0.0001

Data Index: 404153 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1191. Min Act: -0.0001

Data Index: 536229 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1036734 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1087350 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1598541 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1033488 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0979. Min Act: -0.0001

Data Index: 851545 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1028. Min Act: -0.0000

Data Index: 289445 (C4 (Web Text))

Max Activating Token Index: 163