Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1394 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1359062 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0002

Data Index: 383448 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1044087 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0871. Min Act: -0.0002

Data Index: 664432 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0839. Min Act: -0.0002

Data Index: 396471 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1238876 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1030165 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0844. Min Act: -0.0002

Data Index: 233533 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0812. Min Act: -0.0002

Data Index: 260737 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0840. Min Act: -0.0002

Data Index: 784671 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0820. Min Act: -0.0002

Data Index: 735434 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0802. Min Act: -0.0002

Data Index: 257921 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0805. Min Act: -0.0002

Data Index: 748162 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1223590 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0795. Min Act: -0.0002

Data Index: 447960 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1074896 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0799. Min Act: -0.0002

Data Index: 40127 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0825. Min Act: -0.0002

Data Index: 511541 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0793. Min Act: -0.0002

Data Index: 326726 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0783. Min Act: -0.0002

Data Index: 490112 (C4 (Web Text))

Max Activating Token Index: 376