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

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

Neuron 1284 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: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0003

Data Index: 750453 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0466. Min Act: -0.0003

Data Index: 750980 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0447. Min Act: -0.0003

Data Index: 312967 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0447. Min Act: -0.0004

Data Index: 262102 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0423. Min Act: -0.0003

Data Index: 548006 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1077342 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1048260 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0003

Data Index: 804990 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0415. Min Act: -0.0002

Data Index: 224358 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0407. Min Act: -0.0003

Data Index: 664391 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1179879 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1145422 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1038655 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0387. Min Act: -0.0003

Data Index: 823951 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0386. Min Act: -0.0003

Data Index: 560605 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0397. Min Act: -0.0004

Data Index: 1219329 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0395. Min Act: -0.0003

Data Index: 956351 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0380. Min Act: -0.0003

Data Index: 627575 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0368. Min Act: -0.0003

Data Index: 181245 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0386. Min Act: -0.0002

Data Index: 507693 (C4 (Web Text))

Max Activating Token Index: 191