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

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

Neuron 185 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: 0.0425. Min Range: -0.0425

Max Act: 0.0399. Min Act: -0.0005

Data Index: 988805 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0402. Min Act: -0.0005

Data Index: 1329721 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0005

Data Index: 1156307 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0382. Min Act: -0.0005

Data Index: 748986 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0364. Min Act: -0.0005

Data Index: 500070 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0376. Min Act: -0.0005

Data Index: 875152 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0374. Min Act: -0.0005

Data Index: 1277044 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0379. Min Act: -0.0005

Data Index: 1178451 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0368. Min Act: -0.0005

Data Index: 884388 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0368. Min Act: -0.0005

Data Index: 1252537 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0355. Min Act: -0.0005

Data Index: 394676 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0337. Min Act: -0.0005

Data Index: 909426 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0347. Min Act: -0.0005

Data Index: 501084 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0324. Min Act: -0.0005

Data Index: 106505 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0342. Min Act: -0.0005

Data Index: 63740 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0343. Min Act: -0.0005

Data Index: 59251 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0353. Min Act: -0.0005

Data Index: 837599 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0327. Min Act: -0.0005

Data Index: 514762 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0374. Min Act: -0.0005

Data Index: 293838 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0345. Min Act: -0.0005

Data Index: 951047 (C4 (Web Text))

Max Activating Token Index: 578