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

Dataset: The Pile

Neuron 2118 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: 0.8615. Min Range: -0.8615

Max Act: 0.8615. Min Act: -0.0000

Data Index: 87308 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1911641 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.5588. Min Act: -0.0000

Data Index: 361934 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1329481 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1685618 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4618. Min Act: -0.0000

Data Index: 265753 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1462970 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1792906 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1322446 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1101490 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1006074 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4448. Min Act: -0.0000

Data Index: 974513 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4701. Min Act: -0.0000

Data Index: 951836 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1812822 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1258096 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4307. Min Act: -0.0000

Data Index: 1334318 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4259. Min Act: -0.0000

Data Index: 727319 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1993527 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4275. Min Act: -0.0000

Data Index: 850972 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.8615. Min Range: -0.8615

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1473411 (The Pile)

Max Activating Token Index: 916