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

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

Neuron 1547 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: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0006

Data Index: 687849 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0388. Min Act: -0.0006

Data Index: 8363 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0349. Min Act: -0.0006

Data Index: 171739 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1220140 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0371. Min Act: -0.0006

Data Index: 864388 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0352. Min Act: -0.0006

Data Index: 847645 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0345. Min Act: -0.0006

Data Index: 524209 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0333. Min Act: -0.0006

Data Index: 958606 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0316. Min Act: -0.0006

Data Index: 71190 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0314. Min Act: -0.0006

Data Index: 1300917 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1354480 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0325. Min Act: -0.0006

Data Index: 93569 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1197208 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0303. Min Act: -0.0006

Data Index: 818314 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0314. Min Act: -0.0006

Data Index: 643331 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0306. Min Act: -0.0006

Data Index: 942912 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0331. Min Act: -0.0006

Data Index: 349815 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0305. Min Act: -0.0006

Data Index: 872965 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0304. Min Act: -0.0006

Data Index: 241827 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0304. Min Act: -0.0006

Data Index: 840072 (C4 (Web Text))

Max Activating Token Index: 907