Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1426 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1229. Min Act: -0.0003

Data Index: 1636524 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1471401 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1190. Min Act: -0.0003

Data Index: 1502094 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1134. Min Act: -0.0003

Data Index: 1423261 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1121. Min Act: -0.0004

Data Index: 1505199 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1428876 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1528574 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1371807 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1107. Min Act: -0.0002

Data Index: 57862 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1585963 (Python Code)

Max Activating Token Index: 902

Text #10

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1502784 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1365042 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1098. Min Act: -0.0003

Data Index: 1613239 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1063. Min Act: -0.0003

Data Index: 574715 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1041. Min Act: -0.0003

Data Index: 1445731 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1025. Min Act: -0.0003

Data Index: 1491530 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0974. Min Act: -0.0003

Data Index: 1494234 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1024. Min Act: -0.0003

Data Index: 931782 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1034. Min Act: -0.0003

Data Index: 1000408 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1452431 (Python Code)

Max Activating Token Index: 903