Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3041 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9563. Min Act: -0.0003

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8780. Min Act: -0.0003

Data Index: 1325379 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8443. Min Act: -0.0003

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8002. Min Act: -0.0003

Data Index: 202629 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7053. Min Act: -0.0003

Data Index: 1174752 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7033. Min Act: -0.0003

Data Index: 863261 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7834. Min Act: -0.0003

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6733. Min Act: -0.0003

Data Index: 443476 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6890. Min Act: -0.0003

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7906. Min Act: -0.0003

Data Index: 622757 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6301. Min Act: -0.0003

Data Index: 164584 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7079. Min Act: -0.0003

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6753. Min Act: -0.0003

Data Index: 107119 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7072. Min Act: -0.0003

Data Index: 505526 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7064. Min Act: -0.0003

Data Index: 1276149 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6941. Min Act: -0.0003

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6219. Min Act: -0.0003

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6249. Min Act: -0.0003

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6879. Min Act: -0.0003

Data Index: 782979 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6675. Min Act: -0.0003

Data Index: 185251 (C4 (Web Text))

Max Activating Token Index: 183