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

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

Neuron 662 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: 0.1244. Min Range: -0.1244

Max Act: 0.1216. Min Act: -0.0002

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1457070 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0002

Data Index: 496419 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1036. Min Act: -0.0003

Data Index: 1514285 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1335633 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1058. Min Act: -0.0003

Data Index: 1524280 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1125. Min Act: -0.0004

Data Index: 1570343 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1618743 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1045. Min Act: -0.0003

Data Index: 1338386 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1625571 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1033. Min Act: -0.0003

Data Index: 406531 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1014. Min Act: -0.0002

Data Index: 996116 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1004. Min Act: -0.0002

Data Index: 507571 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1524299 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1038. Min Act: -0.0003

Data Index: 1428678 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0990. Min Act: -0.0002

Data Index: 476095 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1592425 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1058. Min Act: -0.0003

Data Index: 1621405 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0890. Min Act: -0.0002

Data Index: 395815 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1550346 (Python Code)

Max Activating Token Index: 277