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

Dataset: The Pile

Neuron 3593 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: 0.9502. Min Range: -0.9502

Max Act: 0.9502. Min Act: -0.0000

Data Index: 660272 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1898211 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1221307 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1056330 (The Pile)

Max Activating Token Index: 567

Text #4

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1111586 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1372538 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1183712 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7966. Min Act: -0.0000

Data Index: 122667 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7796. Min Act: -0.0000

Data Index: 236867 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7716. Min Act: -0.0000

Data Index: 129830 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1090581 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7782. Min Act: -0.0000

Data Index: 151389 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1204794 (The Pile)

Max Activating Token Index: 490

Text #13

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.8705. Min Act: -0.0000

Data Index: 611438 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1239056 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.7216. Min Act: -0.0000

Data Index: 108815 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6707. Min Act: -0.0000

Data Index: 126646 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1201412 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1826190 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 0.9502. Min Range: -0.9502

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1608909 (The Pile)

Max Activating Token Index: 315