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

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

Neuron 930 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: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0006

Data Index: 771020 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0342. Min Act: -0.0006

Data Index: 810576 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0314. Min Act: -0.0006

Data Index: 937425 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0319. Min Act: -0.0006

Data Index: 623727 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0319. Min Act: -0.0006

Data Index: 620665 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0313. Min Act: -0.0006

Data Index: 940896 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0309. Min Act: -0.0006

Data Index: 428409 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0316. Min Act: -0.0006

Data Index: 638463 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1156854 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0309. Min Act: -0.0006

Data Index: 341445 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1236670 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0318. Min Act: -0.0006

Data Index: 1110605 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1280370 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0305. Min Act: -0.0006

Data Index: 863814 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0313. Min Act: -0.0006

Data Index: 51715 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0298. Min Act: -0.0006

Data Index: 668923 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0310. Min Act: -0.0006

Data Index: 743981 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0305. Min Act: -0.0006

Data Index: 350568 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0297. Min Act: -0.0006

Data Index: 611227 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0308. Min Act: -0.0006

Data Index: 544170 (C4 (Web Text))

Max Activating Token Index: 119