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

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

Neuron 4308 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: 8.0301. Min Range: -8.0301

Max Act: 8.0301. Min Act: -0.0000

Data Index: 1516206 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.3007. Min Act: -0.0000

Data Index: 655174 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.5507. Min Act: -0.0000

Data Index: 475730 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.2890. Min Act: -0.0000

Data Index: 825547 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.2879. Min Act: -0.0000

Data Index: 332028 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1992. Min Act: -0.0000

Data Index: 966301 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.2035. Min Act: -0.0000

Data Index: 202992 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1070841 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.2065. Min Act: -0.0000

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1330495 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1647. Min Act: -0.0000

Data Index: 726247 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1464. Min Act: -0.0000

Data Index: 301128 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1761. Min Act: -0.0000

Data Index: 646922 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1346. Min Act: -0.0000

Data Index: 673963 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1883. Min Act: -0.0000

Data Index: 189755 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1548. Min Act: -0.0000

Data Index: 22771 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1748. Min Act: -0.0000

Data Index: 379962 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1095981 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 8.0301. Min Range: -8.0301

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1234819 (C4 (Web Text))

Max Activating Token Index: 726