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

Dataset: The Pile

Neuron 2942 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: 0.3590. Min Range: -0.3590

Max Act: 0.3590. Min Act: -0.0000

Data Index: 806730 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3514. Min Act: -0.0000

Data Index: 1779909 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3455. Min Act: -0.0000

Data Index: 565073 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1392459 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1786260 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1172886 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1280838 (The Pile)

Max Activating Token Index: 569

Text #7

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1352313 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1511099 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1565311 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1865899 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2928. Min Act: -0.0000

Data Index: 462647 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2762. Min Act: -0.0000

Data Index: 414090 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2665. Min Act: -0.0000

Data Index: 617903 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2623. Min Act: -0.0000

Data Index: 790885 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2564. Min Act: -0.0000

Data Index: 641286 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1960865 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2550. Min Act: -0.0000

Data Index: 660971 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2558. Min Act: -0.0000

Data Index: 106489 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1848505 (The Pile)

Max Activating Token Index: 377