Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 49 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0002

Data Index: 946954 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1184982 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0513. Min Act: -0.0003

Data Index: 582750 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0471. Min Act: -0.0003

Data Index: 807486 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0429. Min Act: -0.0003

Data Index: 582228 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1072827 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0407. Min Act: -0.0003

Data Index: 104367 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1015289 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0421. Min Act: -0.0003

Data Index: 415384 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0420. Min Act: -0.0003

Data Index: 733318 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0417. Min Act: -0.0003

Data Index: 286996 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0422. Min Act: -0.0002

Data Index: 496713 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0407. Min Act: -0.0003

Data Index: 837729 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1129689 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0402. Min Act: -0.0003

Data Index: 747923 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1238740 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0386. Min Act: -0.0003

Data Index: 266844 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0389. Min Act: -0.0003

Data Index: 254393 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1156184 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0377. Min Act: -0.0003

Data Index: 364067 (C4 (Web Text))

Max Activating Token Index: 995