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

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

Neuron 2019 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: 0.0401. Min Range: -0.0401

Max Act: 0.0398. Min Act: -0.0005

Data Index: 236156 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1126652 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0370. Min Act: -0.0005

Data Index: 806562 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0366. Min Act: -0.0005

Data Index: 940387 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1238037 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0381. Min Act: -0.0005

Data Index: 164382 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0366. Min Act: -0.0005

Data Index: 868481 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0362. Min Act: -0.0005

Data Index: 1175949 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1169564 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0346. Min Act: -0.0005

Data Index: 33115 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0341. Min Act: -0.0005

Data Index: 219955 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0332. Min Act: -0.0005

Data Index: 171101 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1286312 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0323. Min Act: -0.0005

Data Index: 316164 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0335. Min Act: -0.0005

Data Index: 7078 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0334. Min Act: -0.0005

Data Index: 222568 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0318. Min Act: -0.0005

Data Index: 1231554 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0331. Min Act: -0.0005

Data Index: 376292 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0330. Min Act: -0.0005

Data Index: 530540 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0316. Min Act: -0.0005

Data Index: 997910 (C4 (Web Text))

Max Activating Token Index: 725