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

Dataset: The Pile

Neuron 1732 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: 1.7425. Min Range: -1.7425

Max Act: 1.7425. Min Act: -0.0000

Data Index: 656430 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.7425. Min Range: -1.7425

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1300666 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 1.7425. Min Range: -1.7425

Max Act: 1.0554. Min Act: -0.0000

Data Index: 801964 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9608. Min Act: -0.0000

Data Index: 394123 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9321. Min Act: 0.0000

Data Index: 847074 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9395. Min Act: -0.0000

Data Index: 376189 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1273902 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9793. Min Act: -0.0000

Data Index: 952441 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1525429 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1146172 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1268571 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.9017. Min Act: -0.0000

Data Index: 118193 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8684. Min Act: -0.0000

Data Index: 542110 (The Pile)

Max Activating Token Index: 920

Text #13

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8467. Min Act: -0.0000

Data Index: 779797 (The Pile)

Max Activating Token Index: 684

Text #14

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1344250 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8379. Min Act: -0.0000

Data Index: 783580 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.7858. Min Act: -0.0000

Data Index: 239748 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8656. Min Act: -0.0000

Data Index: 901240 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1164045 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 1.7425. Min Range: -1.7425

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1693916 (The Pile)

Max Activating Token Index: 404