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

Dataset: The Pile

Neuron 3872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4485. Min Act: -0.0000

Data Index: 689704 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1735652 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4019. Min Act: -0.0000

Data Index: 397119 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1762621 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3962. Min Act: -0.0000

Data Index: 778514 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1844493 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1601817 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1401795 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3585. Min Act: -0.0000

Data Index: 212807 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3789. Min Act: -0.0000

Data Index: 43402 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3917. Min Act: -0.0000

Data Index: 196943 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1521312 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3601. Min Act: -0.0000

Data Index: 733451 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3662. Min Act: -0.0000

Data Index: 218883 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3106. Min Act: -0.0000

Data Index: 401986 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3270. Min Act: -0.0000

Data Index: 774845 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1646012 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1044400 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3325. Min Act: -0.0000

Data Index: 39917 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 0.4485. Min Range: -0.4485

Max Act: 0.3219. Min Act: -0.0000

Data Index: 178523 (The Pile)

Max Activating Token Index: 802