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

Dataset: The Pile

Neuron 3665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3228. Min Act: -0.0000

Data Index: 179929 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1215179 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1311633 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2787. Min Act: -0.0000

Data Index: 969190 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2801. Min Act: -0.0000

Data Index: 558590 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2877. Min Act: -0.0000

Data Index: 782991 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1735477 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2738. Min Act: -0.0000

Data Index: 764842 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2787. Min Act: -0.0000

Data Index: 193647 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2566. Min Act: -0.0000

Data Index: 839400 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1044332 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1344591 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1885485 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2625. Min Act: -0.0000

Data Index: 99503 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2794. Min Act: 0.0000

Data Index: 1429469 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1263452 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2444. Min Act: -0.0000

Data Index: 300331 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2513. Min Act: -0.0000

Data Index: 238852 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1414810 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2360. Min Act: -0.0000

Data Index: 557351 (The Pile)

Max Activating Token Index: 3