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

Dataset: The Pile

Neuron 3826 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: 0.4291. Min Range: -0.4291

Max Act: 0.4291. Min Act: -0.0000

Data Index: 551978 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4077. Min Act: -0.0000

Data Index: 736379 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1190271 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3522. Min Act: -0.0000

Data Index: 197028 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1551801 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1519433 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4095. Min Act: -0.0000

Data Index: 995406 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3603. Min Act: -0.0000

Data Index: 905681 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3927. Min Act: -0.0000

Data Index: 194641 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1263725 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1371889 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1928965 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2601. Min Act: -0.0000

Data Index: 737455 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1217137 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3099. Min Act: -0.0000

Data Index: 657954 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1425203 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1623114 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1821981 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1371080 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1655367 (The Pile)

Max Activating Token Index: 340