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

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

Neuron 1433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1210014 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0446. Min Act: -0.0005

Data Index: 1172998 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0426. Min Act: -0.0005

Data Index: 762715 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0408. Min Act: -0.0005

Data Index: 375902 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0413. Min Act: -0.0005

Data Index: 148313 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0394. Min Act: -0.0005

Data Index: 1080337 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0392. Min Act: -0.0005

Data Index: 16499 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0395. Min Act: -0.0005

Data Index: 362479 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0409. Min Act: -0.0005

Data Index: 642844 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0393. Min Act: -0.0005

Data Index: 853303 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0383. Min Act: -0.0005

Data Index: 1101981 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0396. Min Act: -0.0005

Data Index: 114858 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0386. Min Act: -0.0005

Data Index: 439614 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1272235 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0382. Min Act: -0.0005

Data Index: 576381 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1342349 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0375. Min Act: -0.0005

Data Index: 141423 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0375. Min Act: -0.0005

Data Index: 860564 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0381. Min Act: -0.0005

Data Index: 182008 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0383. Min Act: -0.0005

Data Index: 39544 (C4 (Web Text))

Max Activating Token Index: 299