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

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

Neuron 480 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: 0.2382. Min Range: -0.2382

Max Act: 0.2382. Min Act: -0.0000

Data Index: 733110 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1337301 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1381543 (Python Code)

Max Activating Token Index: 738

Text #3

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1163. Min Act: -0.0000

Data Index: 226163 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1429817 (Python Code)

Max Activating Token Index: 402

Text #5

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1077. Min Act: -0.0000

Data Index: 298189 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1554865 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1578413 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1149572 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1586541 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1448654 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1482783 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1430040 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1425098 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1413735 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1431657 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1005. Min Act: -0.0000

Data Index: 40348 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1408349 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1007142 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.2382. Min Range: -0.2382

Max Act: 0.0919. Min Act: -0.0000

Data Index: 572793 (C4 (Web Text))

Max Activating Token Index: 339