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

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

Neuron 5500 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: 2.3679. Min Range: -2.3679

Max Act: 2.0230. Min Act: -0.0000

Data Index: 30922 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 2.3679. Min Range: -2.3679

Max Act: 2.3679. Min Act: -0.0000

Data Index: 641210 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.7499. Min Act: -0.0000

Data Index: 1249860 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.6644. Min Act: -0.0000

Data Index: 756944 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.7391. Min Act: -0.0000

Data Index: 213665 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.7826. Min Act: -0.0000

Data Index: 472494 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.7943. Min Act: -0.0000

Data Index: 445477 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.5751. Min Act: -0.0000

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.3800. Min Act: -0.0000

Data Index: 466890 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.3614. Min Act: -0.0000

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.3394. Min Act: -0.0000

Data Index: 143402 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.3630. Min Act: -0.0000

Data Index: 858318 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.4393. Min Act: -0.0000

Data Index: 519938 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.4065. Min Act: -0.0000

Data Index: 991655 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1084461 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.2736. Min Act: -0.0000

Data Index: 369272 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.1836. Min Act: -0.0000

Data Index: 199161 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.1935. Min Act: -0.0000

Data Index: 367336 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.1957. Min Act: -0.0000

Data Index: 420226 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 2.3679. Min Range: -2.3679

Max Act: 1.2261. Min Act: -0.0000

Data Index: 461659 (C4 (Web Text))

Max Activating Token Index: 26