Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1751 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0003

Data Index: 905766 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0908. Min Act: -0.0003

Data Index: 1244852 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0873. Min Act: -0.0003

Data Index: 101902 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0917. Min Act: -0.0003

Data Index: 593099 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1573719 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0846. Min Act: -0.0003

Data Index: 634334 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0857. Min Act: -0.0003

Data Index: 966094 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0888. Min Act: -0.0003

Data Index: 39384 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0843. Min Act: -0.0003

Data Index: 501881 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0835. Min Act: -0.0003

Data Index: 753067 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0807. Min Act: -0.0003

Data Index: 231767 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1252645 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0799. Min Act: -0.0003

Data Index: 699696 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1319337 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0806. Min Act: -0.0003

Data Index: 47855 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1112548 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0842. Min Act: -0.0003

Data Index: 216947 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0813. Min Act: -0.0003

Data Index: 1318755 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0805. Min Act: -0.0003

Data Index: 378947 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0820. Min Act: -0.0003

Data Index: 450678 (C4 (Web Text))

Max Activating Token Index: 200