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

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

Neuron 1642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0003

Data Index: 996649 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1183186 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0446. Min Act: -0.0003

Data Index: 625726 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0379. Min Act: -0.0003

Data Index: 790358 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0382. Min Act: -0.0003

Data Index: 775214 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0391. Min Act: -0.0003

Data Index: 256350 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1132162 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1280069 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1121560 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0394. Min Act: -0.0003

Data Index: 685404 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0362. Min Act: -0.0003

Data Index: 1003155 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0406. Min Act: -0.0002

Data Index: 272499 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1298582 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0392. Min Act: -0.0003

Data Index: 646630 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1284751 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0430. Min Act: -0.0003

Data Index: 854164 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0366. Min Act: -0.0002

Data Index: 721782 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0366. Min Act: -0.0003

Data Index: 452619 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0372. Min Act: -0.0002

Data Index: 637414 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1254729 (C4 (Web Text))

Max Activating Token Index: 20