Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0635. Min Act: -0.0003

Data Index: 610409 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0594. Min Act: -0.0004

Data Index: 1001387 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1065803 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0569. Min Act: -0.0003

Data Index: 920078 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0562. Min Act: -0.0003

Data Index: 239220 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0562. Min Act: -0.0002

Data Index: 682496 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0530. Min Act: -0.0003

Data Index: 428084 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0513. Min Act: -0.0002

Data Index: 840788 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0511. Min Act: -0.0003

Data Index: 459888 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0504. Min Act: -0.0003

Data Index: 180980 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0501. Min Act: -0.0003

Data Index: 911254 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0493. Min Act: -0.0003

Data Index: 676677 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0501. Min Act: -0.0003

Data Index: 257113 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1165289 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0444. Min Act: -0.0003

Data Index: 692323 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0453. Min Act: -0.0003

Data Index: 12400 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0452. Min Act: -0.0003

Data Index: 834293 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0428. Min Act: -0.0003

Data Index: 497025 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0454. Min Act: -0.0003

Data Index: 169367 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.0635. Min Range: -0.0635

Max Act: 0.0439. Min Act: -0.0003

Data Index: 796274 (C4 (Web Text))

Max Activating Token Index: 437