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

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

Neuron 262 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0006

Data Index: 657188 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0392. Min Act: -0.0006

Data Index: 1285289 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0382. Min Act: -0.0006

Data Index: 716725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0364. Min Act: -0.0006

Data Index: 440149 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0380. Min Act: -0.0006

Data Index: 40175 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0346. Min Act: -0.0006

Data Index: 955606 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0367. Min Act: -0.0006

Data Index: 399758 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0366. Min Act: -0.0006

Data Index: 178988 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0350. Min Act: -0.0006

Data Index: 563714 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0319. Min Act: -0.0006

Data Index: 155885 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1313179 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0328. Min Act: -0.0006

Data Index: 588287 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1302746 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1266568 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1334719 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1194146 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0297. Min Act: -0.0006

Data Index: 944273 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0327. Min Act: -0.0006

Data Index: 761530 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0309. Min Act: -0.0006

Data Index: 423050 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0293. Min Act: -0.0006

Data Index: 19911 (C4 (Web Text))

Max Activating Token Index: 621