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

Dataset: The Pile

Neuron 237 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1339. Min Range: -5.1339

Max Act: 5.1339. Min Act: -0.0000

Data Index: 941647 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.6929. Min Act: -0.0000

Data Index: 421605 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.9505. Min Act: -0.0000

Data Index: 1489723 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 5.1339. Min Range: -5.1339

Max Act: 4.0642. Min Act: -0.0000

Data Index: 304751 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.7758. Min Act: -0.0000

Data Index: 1901137 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.7914. Min Act: -0.0000

Data Index: 1291037 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.6035. Min Act: -0.0000

Data Index: 803609 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.5618. Min Act: -0.0000

Data Index: 446286 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.3724. Min Act: -0.0000

Data Index: 553664 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.6768. Min Act: -0.0000

Data Index: 1980272 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4731. Min Act: -0.0000

Data Index: 1194294 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.6545. Min Act: -0.0000

Data Index: 172655 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.5190. Min Act: -0.0000

Data Index: 1644018 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4614. Min Act: -0.0000

Data Index: 672863 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2831. Min Act: -0.0000

Data Index: 1920825 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4289. Min Act: -0.0000

Data Index: 170960 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2188. Min Act: -0.0000

Data Index: 1639705 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.4072. Min Act: -0.0000

Data Index: 1061730 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.2443. Min Act: -0.0000

Data Index: 47408 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 5.1339. Min Range: -5.1339

Max Act: 3.1733. Min Act: -0.0000

Data Index: 1677644 (The Pile)

Max Activating Token Index: 303