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

Dataset: The Pile

Neuron 2653 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: 1.3206. Min Range: -1.3206

Max Act: 1.3206. Min Act: -0.0000

Data Index: 986423 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1707653 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1153. Min Act: -0.0000

Data Index: 335441 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.2966. Min Act: -0.0000

Data Index: 573936 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1808385 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1605609 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1202. Min Act: -0.0000

Data Index: 166042 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1184. Min Act: -0.0000

Data Index: 574971 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0507. Min Act: -0.0000

Data Index: 477969 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9758. Min Act: -0.0000

Data Index: 792151 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.1232. Min Act: -0.0000

Data Index: 613288 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0840. Min Act: -0.0000

Data Index: 363964 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1113510 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0459. Min Act: -0.0000

Data Index: 613713 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0416. Min Act: -0.0000

Data Index: 1929878 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1784764 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1919920 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9703. Min Act: -0.0000

Data Index: 145659 (The Pile)

Max Activating Token Index: 26

Text #18

Max Range: 1.3206. Min Range: -1.3206

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1776980 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 1.3206. Min Range: -1.3206

Max Act: 0.9313. Min Act: -0.0000

Data Index: 874007 (The Pile)

Max Activating Token Index: 392