Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0003

Data Index: 1154994 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0849. Min Act: -0.0003

Data Index: 315678 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0824. Min Act: -0.0003

Data Index: 663258 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0849. Min Act: -0.0004

Data Index: 1272275 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1092043 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0835. Min Act: -0.0003

Data Index: 209708 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0834. Min Act: -0.0003

Data Index: 831490 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0778. Min Act: -0.0004

Data Index: 586605 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0786. Min Act: -0.0003

Data Index: 461482 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0763. Min Act: -0.0003

Data Index: 225813 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0780. Min Act: -0.0002

Data Index: 482881 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0786. Min Act: -0.0003

Data Index: 1264518 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0760. Min Act: -0.0003

Data Index: 588737 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1160734 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0816. Min Act: -0.0003

Data Index: 741416 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0813. Min Act: -0.0003

Data Index: 59508 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0780. Min Act: -0.0003

Data Index: 295484 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0772. Min Act: -0.0003

Data Index: 452012 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0793. Min Act: -0.0003

Data Index: 333273 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0765. Min Act: -0.0003

Data Index: 539940 (C4 (Web Text))

Max Activating Token Index: 245