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

Dataset: The Pile

Neuron 134 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.1531. Min Act: -0.0000

Data Index: 180421 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1814327 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0668. Min Act: -0.0000

Data Index: 546821 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1577455 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1886970 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1320473 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0382. Min Act: -0.0000

Data Index: 197643 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0394. Min Act: -0.0000

Data Index: 892911 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1544195 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 1.1898. Min Range: -1.1898

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1761018 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9411. Min Act: -0.0000

Data Index: 686731 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1198345 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8942. Min Act: -0.0000

Data Index: 246069 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1680762 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1215426 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.9641. Min Act: -0.0000

Data Index: 155895 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.7541. Min Act: -0.0000

Data Index: 841301 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8318. Min Act: -0.0000

Data Index: 270102 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8500. Min Act: -0.0000

Data Index: 749074 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.1898. Min Range: -1.1898

Max Act: 0.8401. Min Act: -0.0000

Data Index: 509722 (The Pile)

Max Activating Token Index: 393