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

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

Neuron 452 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: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0005

Data Index: 957202 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0545. Min Act: -0.0006

Data Index: 704618 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0453. Min Act: -0.0006

Data Index: 192869 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1315983 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0400. Min Act: -0.0006

Data Index: 24205 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0399. Min Act: -0.0006

Data Index: 381156 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0377. Min Act: -0.0006

Data Index: 333874 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0374. Min Act: -0.0006

Data Index: 617673 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0367. Min Act: -0.0006

Data Index: 1044731 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0355. Min Act: -0.0006

Data Index: 765744 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0353. Min Act: -0.0006

Data Index: 391677 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1160262 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0325. Min Act: -0.0006

Data Index: 128518 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1166299 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1037727 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1085262 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0323. Min Act: -0.0006

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0324. Min Act: -0.0006

Data Index: 145448 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1296298 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1270579 (C4 (Web Text))

Max Activating Token Index: 632