Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1313 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0459. Min Act: -0.0003

Data Index: 923752 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0456. Min Act: -0.0003

Data Index: 880746 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0003

Data Index: 45256 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0451. Min Act: -0.0003

Data Index: 145652 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0426. Min Act: -0.0003

Data Index: 119297 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0418. Min Act: -0.0003

Data Index: 890490 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0387. Min Act: -0.0003

Data Index: 85733 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0426. Min Act: -0.0003

Data Index: 254868 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0386. Min Act: -0.0003

Data Index: 462337 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0397. Min Act: -0.0003

Data Index: 179482 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0398. Min Act: -0.0003

Data Index: 499999 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0388. Min Act: -0.0003

Data Index: 635938 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0405. Min Act: -0.0003

Data Index: 651735 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0363. Min Act: -0.0003

Data Index: 671268 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1013439 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0376. Min Act: -0.0003

Data Index: 309716 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0364. Min Act: -0.0003

Data Index: 603561 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0376. Min Act: -0.0003

Data Index: 833228 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1116399 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0354. Min Act: -0.0003

Data Index: 150023 (C4 (Web Text))

Max Activating Token Index: 290