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

Dataset: The Pile

Neuron 262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.3296. Min Act: -0.0000

Data Index: 572464 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1757155 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1034057 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0215. Min Act: -0.0000

Data Index: 168984 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1331400 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 1.3296. Min Range: -1.3296

Max Act: 1.0021. Min Act: -0.0000

Data Index: 874127 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8931. Min Act: -0.0000

Data Index: 663834 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1319546 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9484. Min Act: -0.0000

Data Index: 1943522 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1362320 (The Pile)

Max Activating Token Index: 13

Text #10

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1380657 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8224. Min Act: -0.0000

Data Index: 778381 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.9233. Min Act: -0.0000

Data Index: 842160 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1003895 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1740649 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1502541 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1385582 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8574. Min Act: -0.0000

Data Index: 918098 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.7752. Min Act: -0.0000

Data Index: 254193 (The Pile)

Max Activating Token Index: 62

Text #19

Max Range: 1.3296. Min Range: -1.3296

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1081868 (The Pile)

Max Activating Token Index: 494