Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0001

Data Index: 602806 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0356. Min Act: -0.0001

Data Index: 289133 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1166118 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0001

Data Index: 503401 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0331. Min Act: -0.0001

Data Index: 121179 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0318. Min Act: -0.0001

Data Index: 492983 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0332. Min Act: -0.0001

Data Index: 204601 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0337. Min Act: -0.0001

Data Index: 55827 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0301. Min Act: -0.0001

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1175579 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1193561 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1164659 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0316. Min Act: -0.0001

Data Index: 419526 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1339858 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0315. Min Act: -0.0001

Data Index: 65324 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0328. Min Act: -0.0001

Data Index: 733577 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0316. Min Act: -0.0001

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0319. Min Act: -0.0001

Data Index: 7674 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1431136 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0281. Min Act: -0.0001

Data Index: 521148 (C4 (Web Text))

Max Activating Token Index: 252