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

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

Neuron 4724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2603. Min Act: -0.0002

Data Index: 925754 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0002

Data Index: 869862 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2573. Min Act: -0.0002

Data Index: 1221271 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2515. Min Act: -0.0002

Data Index: 1137947 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2145. Min Act: -0.0002

Data Index: 490435 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2262. Min Act: -0.0002

Data Index: 262656 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2024. Min Act: -0.0002

Data Index: 879174 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1893. Min Act: -0.0002

Data Index: 1311308 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1901. Min Act: -0.0002

Data Index: 1130050 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1290049 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1253692 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1800. Min Act: -0.0002

Data Index: 515149 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1684. Min Act: -0.0002

Data Index: 546709 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1845. Min Act: -0.0002

Data Index: 431695 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1665. Min Act: -0.0002

Data Index: 546048 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1775. Min Act: -0.0002

Data Index: 319399 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1615. Min Act: -0.0002

Data Index: 257255 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1598. Min Act: -0.0002

Data Index: 1199144 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1733. Min Act: -0.0002

Data Index: 908376 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1420. Min Act: -0.0002

Data Index: 177265 (C4 (Web Text))

Max Activating Token Index: 975