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

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

Neuron 2250 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.1785. Min Act: -0.0000

Data Index: 276642 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.3715. Min Act: -0.0000

Data Index: 1147989 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 6.5392. Min Range: -6.5392

Max Act: 6.5392. Min Act: -0.0000

Data Index: 505153 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.7586. Min Act: -0.0000

Data Index: 149971 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.8681. Min Act: -0.0000

Data Index: 766698 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.2883. Min Act: -0.0000

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.6061. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.3923. Min Act: -0.0000

Data Index: 60062 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.1613. Min Act: -0.0000

Data Index: 258228 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.3632. Min Act: -0.0000

Data Index: 301901 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.8225. Min Act: -0.0000

Data Index: 200357 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 6.5392. Min Range: -6.5392

Max Act: 5.0017. Min Act: -0.0000

Data Index: 161407 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.7565. Min Act: -0.0000

Data Index: 1146476 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.7046. Min Act: -0.0000

Data Index: 1045691 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.9941. Min Act: -0.0000

Data Index: 132935 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.7249. Min Act: -0.0000

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.6725. Min Act: -0.0000

Data Index: 113567 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.8433. Min Act: -0.0000

Data Index: 876300 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.8454. Min Act: -0.0000

Data Index: 861168 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 6.5392. Min Range: -6.5392

Max Act: 4.3949. Min Act: -0.0000

Data Index: 1061768 (C4 (Web Text))

Max Activating Token Index: 881