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

Dataset: The Pile

Neuron 482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1829289 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1249432 (The Pile)

Max Activating Token Index: 836

Text #2

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6043. Min Act: -0.0000

Data Index: 934874 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5282. Min Act: -0.0000

Data Index: 102945 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1521741 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5737. Min Act: -0.0000

Data Index: 193999 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1620949 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4808. Min Act: -0.0000

Data Index: 164230 (The Pile)

Max Activating Token Index: 168

Text #8

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1452727 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4672. Min Act: -0.0000

Data Index: 482160 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4626. Min Act: -0.0000

Data Index: 394287 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4566. Min Act: -0.0000

Data Index: 293433 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1948368 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5015. Min Act: -0.0000

Data Index: 975622 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4681. Min Act: -0.0000

Data Index: 148773 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4733. Min Act: -0.0000

Data Index: 114630 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1164015 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4570. Min Act: -0.0000

Data Index: 744412 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4664. Min Act: -0.0000

Data Index: 43256 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1330119 (The Pile)

Max Activating Token Index: 55