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

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

Neuron 3155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1567527 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1564013 (Python Code)

Max Activating Token Index: 550

Text #2

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1490142 (Python Code)

Max Activating Token Index: 353

Text #3

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1370789 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.5885. Min Act: -0.0000

Data Index: 565406 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1439956 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.4528. Min Act: -0.0000

Data Index: 513461 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1102192 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3226. Min Act: -0.0000

Data Index: 259302 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.4056. Min Act: -0.0000

Data Index: 805321 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3590. Min Act: -0.0000

Data Index: 418183 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1505821 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1026942 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3563. Min Act: -0.0000

Data Index: 945524 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2733. Min Act: -0.0000

Data Index: 655750 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1637614 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2981. Min Act: -0.0000

Data Index: 244366 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1319346 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1565039 (Python Code)

Max Activating Token Index: 860

Text #19

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1513828 (Python Code)

Max Activating Token Index: 421