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

Dataset: The Pile

Neuron 2346 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: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0000

Data Index: 616348 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3684. Min Act: -0.0000

Data Index: 422841 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3304. Min Act: -0.0000

Data Index: 442798 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1162960 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1035931 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3672. Min Act: -0.0000

Data Index: 558605 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3185. Min Act: -0.0000

Data Index: 180793 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1908231 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3377. Min Act: -0.0000

Data Index: 916671 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1427872 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1127588 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3260. Min Act: -0.0000

Data Index: 630828 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3015. Min Act: -0.0000

Data Index: 491329 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1357371 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1278603 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2771. Min Act: -0.0000

Data Index: 928606 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1495722 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1080565 (The Pile)

Max Activating Token Index: 70

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1063815 (The Pile)

Max Activating Token Index: 106

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1416301 (The Pile)

Max Activating Token Index: 60