Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1028276 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1054. Min Act: -0.0002

Data Index: 35590 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0002

Data Index: 926923 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0987. Min Act: -0.0002

Data Index: 137500 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1000. Min Act: -0.0002

Data Index: 13600 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0840. Min Act: -0.0002

Data Index: 188731 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1026. Min Act: -0.0002

Data Index: 152891 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1151914 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1036. Min Act: -0.0002

Data Index: 777087 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1033. Min Act: -0.0002

Data Index: 98826 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0949. Min Act: -0.0002

Data Index: 550660 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0941. Min Act: -0.0002

Data Index: 533472 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0876. Min Act: -0.0002

Data Index: 382991 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0844. Min Act: -0.0002

Data Index: 464922 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1306446 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0972. Min Act: -0.0002

Data Index: 58514 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1212327 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0956. Min Act: -0.0002

Data Index: 489798 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0955. Min Act: -0.0002

Data Index: 753196 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0920. Min Act: -0.0002

Data Index: 636567 (C4 (Web Text))

Max Activating Token Index: 56