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

Dataset: The Pile

Neuron 3502 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0517. Min Act: -0.0000

Data Index: 515392 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1357711 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1405622 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1080096 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1999109 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.6262. Min Act: -0.0000

Data Index: 942612 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1226501 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1349422 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1262040 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5847. Min Act: -0.0000

Data Index: 68920 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1945079 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5899. Min Act: -0.0000

Data Index: 543024 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5487. Min Act: -0.0000

Data Index: 609040 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5565. Min Act: -0.0000

Data Index: 216287 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5483. Min Act: -0.0000

Data Index: 122581 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1368055 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1198136 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1470971 (The Pile)

Max Activating Token Index: 174

Text #18

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1388982 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1746433 (The Pile)

Max Activating Token Index: 95