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

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

Neuron 538 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: 0.4844. Min Range: -0.4844

Max Act: 0.4844. Min Act: -0.0000

Data Index: 310014 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3970. Min Act: -0.0000

Data Index: 113246 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3427. Min Act: -0.0000

Data Index: 353506 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3581. Min Act: -0.0000

Data Index: 867812 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1261118 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3386. Min Act: -0.0000

Data Index: 641418 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3025. Min Act: -0.0000

Data Index: 756158 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3291. Min Act: -0.0000

Data Index: 247626 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3043. Min Act: -0.0000

Data Index: 125361 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2962. Min Act: -0.0000

Data Index: 11700 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3065. Min Act: -0.0000

Data Index: 266389 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1050946 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.3139. Min Act: -0.0000

Data Index: 476295 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2762. Min Act: -0.0000

Data Index: 7396 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1280772 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2871. Min Act: -0.0000

Data Index: 19710 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2772. Min Act: -0.0000

Data Index: 284234 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2884. Min Act: -0.0000

Data Index: 387571 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.4844. Min Range: -0.4844

Max Act: 0.2809. Min Act: -0.0000

Data Index: 553502 (C4 (Web Text))

Max Activating Token Index: 284