Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1682 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3560. Min Range: -2.3560

Max Act: 2.3560. Min Act: -0.0000

Data Index: 1279561 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.3539. Min Act: -0.0000

Data Index: 496791 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1645021 (Python Code)

Max Activating Token Index: 484

Text #3

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.3725. Min Act: -0.0000

Data Index: 581013 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.3598. Min Act: -0.0000

Data Index: 1073483 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.3704. Min Act: -0.0000

Data Index: 854076 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.2724. Min Act: -0.0000

Data Index: 349898 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1932. Min Act: -0.0000

Data Index: 586966 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1498. Min Act: -0.0000

Data Index: 57434 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1150. Min Act: -0.0000

Data Index: 721480 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1817. Min Act: -0.0000

Data Index: 347696 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1074. Min Act: -0.0000

Data Index: 936017 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.1047. Min Act: -0.0000

Data Index: 765186 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1330815 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1329655 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 2.3560. Min Range: -2.3560

Max Act: 0.9654. Min Act: -0.0000

Data Index: 413070 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 2.3560. Min Range: -2.3560

Max Act: 1.0472. Min Act: -0.0000

Data Index: 143310 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 2.3560. Min Range: -2.3560

Max Act: 0.9925. Min Act: -0.0000

Data Index: 660957 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 2.3560. Min Range: -2.3560

Max Act: 0.9780. Min Act: -0.0000

Data Index: 266076 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 2.3560. Min Range: -2.3560

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1142477 (C4 (Web Text))

Max Activating Token Index: 404