Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2760 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1190774 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0002

Data Index: 773679 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1114732 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0442. Min Act: -0.0002

Data Index: 154032 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0437. Min Act: -0.0002

Data Index: 876716 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0435. Min Act: -0.0002

Data Index: 67930 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0434. Min Act: -0.0002

Data Index: 145442 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0433. Min Act: -0.0002

Data Index: 124321 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1256403 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0427. Min Act: -0.0002

Data Index: 68431 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1357516 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0421. Min Act: -0.0002

Data Index: 624149 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0419. Min Act: -0.0002

Data Index: 627894 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0418. Min Act: -0.0002

Data Index: 234508 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0418. Min Act: -0.0002

Data Index: 72349 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1136239 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0417. Min Act: -0.0002

Data Index: 325742 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0416. Min Act: -0.0002

Data Index: 137538 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0415. Min Act: -0.0002

Data Index: 508584 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0416. Min Act: -0.0002

Data Index: 376125 (C4 (Web Text))

Max Activating Token Index: 11