Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0001

Data Index: 402660 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0389. Min Act: -0.0002

Data Index: 580399 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0394. Min Act: -0.0002

Data Index: 732965 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0389. Min Act: -0.0002

Data Index: 367738 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1245482 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0356. Min Act: -0.0002

Data Index: 184064 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0368. Min Act: -0.0001

Data Index: 879953 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0358. Min Act: -0.0002

Data Index: 161115 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0355. Min Act: -0.0002

Data Index: 76847 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0352. Min Act: -0.0002

Data Index: 603482 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0355. Min Act: -0.0001

Data Index: 426063 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0359. Min Act: -0.0001

Data Index: 31452 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0343. Min Act: -0.0002

Data Index: 464301 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0347. Min Act: -0.0002

Data Index: 287987 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0344. Min Act: -0.0001

Data Index: 163494 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0341. Min Act: -0.0001

Data Index: 664594 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0343. Min Act: -0.0002

Data Index: 923713 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0330. Min Act: -0.0001

Data Index: 665174 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1057433 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0341. Min Act: -0.0001

Data Index: 169614 (C4 (Web Text))

Max Activating Token Index: 138