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

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

Neuron 3426 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.4548. Min Act: -0.0000

Data Index: 293424 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.4121. Min Act: -0.0000

Data Index: 212192 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.1722. Min Act: -0.0000

Data Index: 421140 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1474226 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1475117 (Python Code)

Max Activating Token Index: 360

Text #5

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1611545 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.0160. Min Act: -0.0000

Data Index: 255489 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.0492. Min Act: -0.0000

Data Index: 357182 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1444088 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 1.4548. Min Range: -1.4548

Max Act: 1.0764. Min Act: -0.0000

Data Index: 732842 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1382350 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1638416 (Python Code)

Max Activating Token Index: 379

Text #12

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.8284. Min Act: -0.0000

Data Index: 337314 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1612295 (Python Code)

Max Activating Token Index: 170

Text #14

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1587852 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1571094 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1477111 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1403914 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1501236 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 1.4548. Min Range: -1.4548

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1532907 (Python Code)

Max Activating Token Index: 863