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

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

Neuron 3751 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: 2.3792. Min Range: -2.3792

Max Act: 2.3792. Min Act: -0.0000

Data Index: 1055464 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1432882 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.8685. Min Act: -0.0000

Data Index: 287303 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.6148. Min Act: -0.0000

Data Index: 436868 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.3483. Min Act: -0.0000

Data Index: 984338 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1443244 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1417596 (Python Code)

Max Activating Token Index: 785

Text #7

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1338822 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1380361 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1215942 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1370349 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.2120. Min Act: -0.0000

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1758. Min Act: -0.0000

Data Index: 738073 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1405113 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1460024 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1503. Min Act: -0.0000

Data Index: 891170 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1673. Min Act: -0.0000

Data Index: 119870 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 2.3792. Min Range: -2.3792

Max Act: 0.9665. Min Act: -0.0000

Data Index: 289894 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.3792. Min Range: -2.3792

Max Act: 1.1203. Min Act: -0.0000

Data Index: 44691 (C4 (Web Text))

Max Activating Token Index: 588