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

Dataset: The Pile

Neuron 1334 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.8720. Min Act: -0.0000

Data Index: 894509 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1412471 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1208077 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1446898 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6006. Min Act: -0.0000

Data Index: 293899 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6007. Min Act: -0.0000

Data Index: 574607 (The Pile)

Max Activating Token Index: 372

Text #6

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1805536 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6085. Min Act: 0.0000

Data Index: 981909 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1996704 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1091572 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1602158 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4793. Min Act: 0.0000

Data Index: 999848 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1183449 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5183. Min Act: 0.0000

Data Index: 1711796 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4844. Min Act: -0.0000

Data Index: 761515 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1132252 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4972. Min Act: 0.0000

Data Index: 1929956 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1311418 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1759696 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1642316 (The Pile)

Max Activating Token Index: 279