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

Dataset: The Pile

Neuron 3310 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: 0.7554. Min Range: -0.7554

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1006201 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6097. Min Act: -0.0000

Data Index: 803697 (The Pile)

Max Activating Token Index: 353

Text #2

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1971718 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5414. Min Act: -0.0000

Data Index: 999703 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5736. Min Act: -0.0000

Data Index: 400046 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6040. Min Act: -0.0000

Data Index: 718147 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5402. Min Act: -0.0000

Data Index: 728359 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1624770 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1789293 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1560866 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1877829 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5049. Min Act: -0.0000

Data Index: 979525 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4600. Min Act: -0.0000

Data Index: 436571 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1311241 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5005. Min Act: -0.0000

Data Index: 148578 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1849648 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1511464 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1968525 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5027. Min Act: -0.0000

Data Index: 232333 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.4664. Min Act: -0.0000

Data Index: 889077 (The Pile)

Max Activating Token Index: 744