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

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

Neuron 4864 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.6052. Min Act: -0.0000

Data Index: 592718 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.6765. Min Act: -0.0000

Data Index: 119272 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1327650 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.5077. Min Act: -0.0000

Data Index: 734372 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.4795. Min Act: -0.0000

Data Index: 784481 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.4664. Min Act: -0.0000

Data Index: 742621 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1035426 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1036941 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3352. Min Act: -0.0000

Data Index: 901419 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3453. Min Act: -0.0000

Data Index: 317385 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3189. Min Act: -0.0000

Data Index: 295422 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.3741. Min Act: -0.0000

Data Index: 22316 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2617. Min Act: -0.0000

Data Index: 600221 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2770. Min Act: -0.0000

Data Index: 356266 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1580624 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1792. Min Act: -0.0000

Data Index: 888809 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1839. Min Act: -0.0000

Data Index: 718417 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.2462. Min Act: -0.0000

Data Index: 304703 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1385. Min Act: -0.0000

Data Index: 147322 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.6765. Min Range: -1.6765

Max Act: 1.1984. Min Act: -0.0000

Data Index: 86105 (C4 (Web Text))

Max Activating Token Index: 26