Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3220 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2680. Min Act: -0.0000

Data Index: 696460 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1935677 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2565. Min Act: -0.0000

Data Index: 265031 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1700907 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1117741 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1970. Min Act: -0.0000

Data Index: 666675 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1392069 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1724801 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1189493 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1237985 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1897555 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2031. Min Act: -0.0000

Data Index: 957790 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1171074 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1157804 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.2024. Min Act: -0.0000

Data Index: 378734 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1893. Min Act: -0.0000

Data Index: 63844 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1995900 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1009689 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1563606 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 0.2680. Min Range: -0.2680

Max Act: 0.1850. Min Act: -0.0000

Data Index: 639866 (The Pile)

Max Activating Token Index: 298