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

Dataset: The Pile

Neuron 4432 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: 0.8145. Min Range: -0.8145

Max Act: 0.8145. Min Act: -0.0000

Data Index: 998911 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1911319 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6694. Min Act: -0.0000

Data Index: 288223 (The Pile)

Max Activating Token Index: 755

Text #3

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6823. Min Act: -0.0000

Data Index: 698710 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1340288 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6901. Min Act: -0.0000

Data Index: 692166 (The Pile)

Max Activating Token Index: 661

Text #6

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1881375 (The Pile)

Max Activating Token Index: 921

Text #7

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6644. Min Act: -0.0001

Data Index: 358643 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1823588 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1718185 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6368. Min Act: -0.0000

Data Index: 404155 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6066. Min Act: -0.0000

Data Index: 673624 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6475. Min Act: -0.0000

Data Index: 213041 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1838946 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1549400 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6567. Min Act: -0.0000

Data Index: 812641 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.5867. Min Act: -0.0000

Data Index: 6650 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6086. Min Act: -0.0000

Data Index: 401086 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1072320 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 0.8145. Min Range: -0.8145

Max Act: 0.6280. Min Act: -0.0000

Data Index: 807821 (The Pile)

Max Activating Token Index: 282