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

Dataset: The Pile

Neuron 764 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: 0.4710. Min Range: -0.4710

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1283543 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4212. Min Act: -0.0000

Data Index: 221812 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4248. Min Act: -0.0000

Data Index: 384580 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.4010. Min Act: -0.0000

Data Index: 465215 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3423. Min Act: -0.0000

Data Index: 849063 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1718959 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3636. Min Act: -0.0000

Data Index: 109338 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3856. Min Act: -0.0000

Data Index: 765468 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3232. Min Act: -0.0000

Data Index: 631775 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1647997 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2988. Min Act: -0.0000

Data Index: 572844 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2901. Min Act: -0.0000

Data Index: 989568 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2738. Min Act: -0.0000

Data Index: 290630 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1185043 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1505699 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2979. Min Act: -0.0000

Data Index: 59138 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1924177 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1757415 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.4710. Min Range: -0.4710

Max Act: 0.2724. Min Act: -0.0000

Data Index: 283584 (The Pile)

Max Activating Token Index: 486