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

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

Neuron 1447 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5743. Min Range: -4.5743

Max Act: 4.5743. Min Act: -0.0000

Data Index: 34575 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.6454. Min Act: -0.0000

Data Index: 1241463 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.5674. Min Act: -0.0000

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.5259. Min Act: -0.0000

Data Index: 703916 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.3805. Min Act: -0.0001

Data Index: 327655 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.4964. Min Act: -0.0000

Data Index: 380365 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.3931. Min Act: -0.0000

Data Index: 516105 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.2513. Min Act: -0.0000

Data Index: 230094 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.0793. Min Act: -0.0000

Data Index: 49631 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.3563. Min Act: -0.0000

Data Index: 907132 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.4969. Min Act: -0.0000

Data Index: 447977 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.1700. Min Act: -0.0000

Data Index: 276725 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.0277. Min Act: -0.0000

Data Index: 462062 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.1463. Min Act: -0.0000

Data Index: 679050 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.1252. Min Act: -0.0000

Data Index: 986710 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.2422. Min Act: -0.0000

Data Index: 744392 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.0920. Min Act: -0.0000

Data Index: 1252736 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.1003. Min Act: -0.0000

Data Index: 810584 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.4833. Min Act: -0.0000

Data Index: 741048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.5743. Min Range: -4.5743

Max Act: 3.0747. Min Act: -0.0000

Data Index: 737169 (C4 (Web Text))

Max Activating Token Index: 999