Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5422 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1775. Min Act: -0.0000

Data Index: 485707 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.9421. Min Act: -0.0000

Data Index: 377360 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8898. Min Act: -0.0000

Data Index: 1200044 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.8736. Min Act: -0.0000

Data Index: 709348 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3903. Min Act: -0.0000

Data Index: 915083 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.6311. Min Act: -0.0000

Data Index: 812944 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4029. Min Act: -0.0000

Data Index: 842023 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3645. Min Act: -0.0000

Data Index: 118194 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4348. Min Act: -0.0000

Data Index: 113531 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.2005. Min Act: -0.0000

Data Index: 485527 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3099. Min Act: -0.0000

Data Index: 393934 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.2702. Min Act: -0.0000

Data Index: 461383 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1971. Min Act: -0.0000

Data Index: 112678 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.0513. Min Act: -0.0000

Data Index: 712225 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1063414 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1039999 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1008. Min Act: -0.0000

Data Index: 223709 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1064539 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.1277. Min Act: -0.0000

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.0971. Min Act: 0.0000

Data Index: 112487 (C4 (Web Text))

Max Activating Token Index: 66