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

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

Neuron 472 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: 0.0518. Min Range: -0.0518

Max Act: 0.0518. Min Act: -0.0005

Data Index: 168912 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0417. Min Act: -0.0005

Data Index: 223838 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0416. Min Act: -0.0005

Data Index: 913363 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0413. Min Act: -0.0005

Data Index: 1112868 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0390. Min Act: -0.0005

Data Index: 386862 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0402. Min Act: -0.0005

Data Index: 576612 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0414. Min Act: -0.0005

Data Index: 183127 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1047808 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1164589 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0373. Min Act: -0.0005

Data Index: 874005 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0345. Min Act: -0.0005

Data Index: 598767 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0355. Min Act: -0.0005

Data Index: 963457 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1329356 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0337. Min Act: -0.0005

Data Index: 700582 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0357. Min Act: -0.0005

Data Index: 292983 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0339. Min Act: -0.0005

Data Index: 399791 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0343. Min Act: -0.0005

Data Index: 1380676 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0332. Min Act: -0.0005

Data Index: 751255 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0332. Min Act: -0.0005

Data Index: 991885 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.0518. Min Range: -0.0518

Max Act: 0.0352. Min Act: -0.0005

Data Index: 810833 (C4 (Web Text))

Max Activating Token Index: 850