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

Dataset: The Pile

Neuron 4020 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: 1.7557. Min Range: -1.7557

Max Act: 1.5688. Min Act: -0.0000

Data Index: 364226 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.6356. Min Act: -0.0000

Data Index: 1778967 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1637023 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5522. Min Act: -0.0000

Data Index: 1004407 (The Pile)

Max Activating Token Index: 766

Text #4

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5743. Min Act: -0.0000

Data Index: 289055 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.4314. Min Act: -0.0000

Data Index: 152207 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.4370. Min Act: -0.0000

Data Index: 248422 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3762. Min Act: -0.0000

Data Index: 694319 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5289. Min Act: -0.0000

Data Index: 938349 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.7557. Min Act: -0.0000

Data Index: 523560 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1711611 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3471. Min Act: -0.0000

Data Index: 831104 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5015. Min Act: -0.0000

Data Index: 301612 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3666. Min Act: -0.0000

Data Index: 947112 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5352. Min Act: -0.0000

Data Index: 108495 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1505583 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3967. Min Act: -0.0000

Data Index: 62112 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1012163 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.4329. Min Act: -0.0000

Data Index: 734808 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 1.7557. Min Range: -1.7557

Max Act: 1.3798. Min Act: -0.0000

Data Index: 543963 (The Pile)

Max Activating Token Index: 685