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

Dataset: The Pile

Neuron 1349 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: 1.4508. Min Range: -1.4508

Max Act: 1.4508. Min Act: -0.0000

Data Index: 65955 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4037. Min Act: -0.0000

Data Index: 874495 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1589027 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2732. Min Act: -0.0000

Data Index: 589614 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1150355 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1912. Min Act: -0.0000

Data Index: 169008 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1737. Min Act: -0.0000

Data Index: 80356 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1470609 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1415714 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1383677 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9468. Min Act: -0.0000

Data Index: 811542 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0248. Min Act: -0.0000

Data Index: 243915 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1988386 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0581. Min Act: -0.0000

Data Index: 394419 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1019195 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1325386 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1775088 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1354271 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9835. Min Act: -0.0000

Data Index: 493136 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1757175 (The Pile)

Max Activating Token Index: 160