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

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

Neuron 451 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0006

Data Index: 526037 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1478353 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0312. Min Act: -0.0006

Data Index: 1016372 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0302. Min Act: -0.0006

Data Index: 1456613 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0316. Min Act: -0.0006

Data Index: 757687 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0305. Min Act: -0.0006

Data Index: 886403 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0303. Min Act: -0.0006

Data Index: 516167 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0293. Min Act: -0.0006

Data Index: 851518 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0299. Min Act: -0.0006

Data Index: 405173 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1476926 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1386152 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1198952 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1603295 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1361865 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0287. Min Act: -0.0006

Data Index: 560660 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1440104 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0291. Min Act: -0.0005

Data Index: 5404 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1517220 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0289. Min Act: -0.0006

Data Index: 791060 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0282. Min Act: -0.0006

Data Index: 207675 (C4 (Web Text))

Max Activating Token Index: 564