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

Dataset: The Pile

Neuron 1964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.8837. Min Act: -0.0000

Data Index: 345588 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1345615 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1123399 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1113642 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1925527 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7341. Min Act: 0.0000

Data Index: 776849 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7207. Min Act: -0.0000

Data Index: 936673 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1179065 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1693140 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1693630 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.7147. Min Act: -0.0000

Data Index: 616846 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6687. Min Act: -0.0000

Data Index: 483886 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1397548 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6387. Min Act: -0.0000

Data Index: 463162 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1117322 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1062647 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1678390 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1483642 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1341979 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.8837. Min Range: -0.8837

Max Act: 0.6107. Min Act: -0.0000

Data Index: 959864 (The Pile)

Max Activating Token Index: 25