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

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

Neuron 1748 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0000

Data Index: 6084 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1188. Min Act: -0.0000

Data Index: 581645 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1578144 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1326. Min Act: -0.0000

Data Index: 754720 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1321513 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1245. Min Act: -0.0000

Data Index: 461790 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1239858 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1224. Min Act: -0.0000

Data Index: 205743 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1145. Min Act: -0.0000

Data Index: 917975 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1183. Min Act: -0.0000

Data Index: 373524 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1611536 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1253. Min Act: -0.0000

Data Index: 947698 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1312443 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1299125 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1192. Min Act: -0.0000

Data Index: 801178 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1115. Min Act: -0.0000

Data Index: 829821 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1089261 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1065. Min Act: -0.0000

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1099. Min Act: -0.0000

Data Index: 298158 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1171070 (C4 (Web Text))

Max Activating Token Index: 512