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

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

Neuron 1994 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1300833 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1023031 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0371. Min Act: -0.0003

Data Index: 10878 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0374. Min Act: -0.0003

Data Index: 215297 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0362. Min Act: -0.0003

Data Index: 218664 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0353. Min Act: -0.0003

Data Index: 626195 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0346. Min Act: -0.0003

Data Index: 594364 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0342. Min Act: -0.0002

Data Index: 219158 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1284043 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1191123 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1157414 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0335. Min Act: -0.0003

Data Index: 491501 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0339. Min Act: -0.0003

Data Index: 813425 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0340. Min Act: -0.0003

Data Index: 395037 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0337. Min Act: -0.0003

Data Index: 681679 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1100067 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1268161 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0341. Min Act: -0.0003

Data Index: 789471 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0328. Min Act: -0.0003

Data Index: 600082 (C4 (Web Text))

Max Activating Token Index: 230