Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 627 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0006

Data Index: 720803 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0337. Min Act: -0.0006

Data Index: 897351 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0362. Min Act: -0.0006

Data Index: 254475 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0350. Min Act: -0.0006

Data Index: 1166494 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0341. Min Act: -0.0006

Data Index: 957280 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0320. Min Act: -0.0006

Data Index: 16016 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0306. Min Act: -0.0006

Data Index: 685555 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0353. Min Act: -0.0006

Data Index: 559773 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0317. Min Act: -0.0006

Data Index: 20937 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0308. Min Act: -0.0006

Data Index: 925803 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0299. Min Act: -0.0006

Data Index: 187209 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0318. Min Act: -0.0006

Data Index: 299789 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0304. Min Act: -0.0006

Data Index: 554232 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1180768 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0309. Min Act: -0.0006

Data Index: 765837 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0318. Min Act: -0.0006

Data Index: 618024 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0299. Min Act: -0.0006

Data Index: 285987 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1177757 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0296. Min Act: -0.0006

Data Index: 920803 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0301. Min Act: -0.0006

Data Index: 771715 (C4 (Web Text))

Max Activating Token Index: 402