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

Dataset: The Pile

Neuron 298 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: 0.4781. Min Range: -0.4781

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1459563 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1878070 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1970571 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1603297 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3807. Min Act: -0.0000

Data Index: 470016 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1805759 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1898720 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3454. Min Act: -0.0000

Data Index: 99158 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3538. Min Act: -0.0000

Data Index: 682420 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3214. Min Act: -0.0000

Data Index: 630210 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1470650 (The Pile)

Max Activating Token Index: 672

Text #11

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1765580 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3240. Min Act: -0.0000

Data Index: 1569029 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3447. Min Act: -0.0000

Data Index: 588494 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3508. Min Act: -0.0000

Data Index: 138337 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1890674 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3240. Min Act: -0.0000

Data Index: 688946 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3252. Min Act: -0.0000

Data Index: 130777 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1287858 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3283. Min Act: -0.0000

Data Index: 910319 (The Pile)

Max Activating Token Index: 342