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

Dataset: The Pile

Neuron 1452 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: 1.0962. Min Range: -1.0962

Max Act: 1.0962. Min Act: -0.0000

Data Index: 1809296 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1881464 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.9309. Min Act: -0.0000

Data Index: 452711 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1383857 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8639. Min Act: -0.0000

Data Index: 630660 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8358. Min Act: -0.0000

Data Index: 203823 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8805. Min Act: -0.0000

Data Index: 937926 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8613. Min Act: -0.0000

Data Index: 559222 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8494. Min Act: -0.0000

Data Index: 274545 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1673925 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1589304 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8430. Min Act: -0.0000

Data Index: 173742 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8993. Min Act: -0.0000

Data Index: 34015 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8266. Min Act: -0.0000

Data Index: 130566 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1736696 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7594. Min Act: -0.0000

Data Index: 835700 (The Pile)

Max Activating Token Index: 149

Text #16

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8306. Min Act: -0.0000

Data Index: 21930 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1237548 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1069241 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.0962. Min Range: -1.0962

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1798364 (The Pile)

Max Activating Token Index: 438