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

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

Neuron 761 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1226. Min Act: -0.0000

Data Index: 572826 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1248608 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1069. Min Act: -0.0000

Data Index: 391763 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1026. Min Act: -0.0000

Data Index: 152325 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0993. Min Act: -0.0000

Data Index: 912875 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.1047. Min Act: -0.0000

Data Index: 671045 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0956. Min Act: -0.0000

Data Index: 415659 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0970. Min Act: -0.0000

Data Index: 103418 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1461432 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0987. Min Act: -0.0000

Data Index: 86136 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0947. Min Act: -0.0000

Data Index: 961533 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1426928 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1596963 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0866. Min Act: -0.0000

Data Index: 673564 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1405403 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1477032 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0879. Min Act: -0.0000

Data Index: 764528 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0826. Min Act: -0.0000

Data Index: 255790 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1425685 (Python Code)

Max Activating Token Index: 970

Text #19

Max Range: 0.1226. Min Range: -0.1226

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1411340 (Python Code)

Max Activating Token Index: 844