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

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

Neuron 666 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0418. Min Act: -0.0005

Data Index: 1237948 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0005

Data Index: 530499 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1041675 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0401. Min Act: -0.0005

Data Index: 128097 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0352. Min Act: -0.0005

Data Index: 440458 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0361. Min Act: -0.0005

Data Index: 1078137 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0349. Min Act: -0.0005

Data Index: 217209 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0349. Min Act: -0.0005

Data Index: 275709 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0344. Min Act: -0.0005

Data Index: 1200128 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0337. Min Act: -0.0005

Data Index: 790771 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0332. Min Act: -0.0005

Data Index: 20370 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0324. Min Act: -0.0005

Data Index: 1117830 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0270. Min Act: -0.0005

Data Index: 935627 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0315. Min Act: -0.0005

Data Index: 1143766 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0313. Min Act: -0.0005

Data Index: 632989 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0322. Min Act: -0.0005

Data Index: 841468 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0329. Min Act: -0.0005

Data Index: 738439 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0311. Min Act: -0.0005

Data Index: 1103304 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0317. Min Act: -0.0005

Data Index: 1079998 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0317. Min Act: -0.0005

Data Index: 10573 (C4 (Web Text))

Max Activating Token Index: 368