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

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

Neuron 1589 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: 0.0470. Min Range: -0.0470

Max Act: 0.0465. Min Act: -0.0003

Data Index: 346261 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1231452 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0427. Min Act: -0.0002

Data Index: 584274 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0419. Min Act: -0.0003

Data Index: 622946 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0416. Min Act: -0.0003

Data Index: 214443 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0394. Min Act: -0.0003

Data Index: 708559 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0386. Min Act: -0.0003

Data Index: 585775 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0370. Min Act: -0.0003

Data Index: 893088 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1147874 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0370. Min Act: -0.0003

Data Index: 561084 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0366. Min Act: -0.0004

Data Index: 135821 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0369. Min Act: -0.0004

Data Index: 41740 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1194941 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0355. Min Act: -0.0003

Data Index: 268417 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1167794 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0367. Min Act: -0.0003

Data Index: 60931 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1056838 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0357. Min Act: -0.0004

Data Index: 399737 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0355. Min Act: -0.0004

Data Index: 906399 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0348. Min Act: -0.0002

Data Index: 926717 (C4 (Web Text))

Max Activating Token Index: 781