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

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

Neuron 1359 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: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0002

Data Index: 423816 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0912. Min Act: -0.0002

Data Index: 923546 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0886. Min Act: -0.0002

Data Index: 584308 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0775. Min Act: -0.0002

Data Index: 299379 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1139398 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0779. Min Act: -0.0002

Data Index: 827989 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1255489 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1186680 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0699. Min Act: -0.0002

Data Index: 699024 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1072819 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1107139 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1096376 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0756. Min Act: -0.0002

Data Index: 319621 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0725. Min Act: -0.0002

Data Index: 584754 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0727. Min Act: -0.0002

Data Index: 224723 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1152967 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0725. Min Act: -0.0002

Data Index: 525316 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0732. Min Act: -0.0002

Data Index: 141148 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0721. Min Act: -0.0001

Data Index: 438830 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0727. Min Act: -0.0002

Data Index: 410889 (C4 (Web Text))

Max Activating Token Index: 527