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

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

Neuron 4229 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: 0.6660. Min Range: -0.6660

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1563460 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1476503 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1001167 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1457263 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1481502 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1624677 (Python Code)

Max Activating Token Index: 904

Text #6

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1638263 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5851. Min Act: -0.0000

Data Index: 285068 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5599. Min Act: -0.0000

Data Index: 176256 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1627884 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1364166 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1479194 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1625608 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1368626 (Python Code)

Max Activating Token Index: 727

Text #14

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1550081 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.5390. Min Act: -0.0000

Data Index: 64006 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4932. Min Act: -0.0000

Data Index: 990506 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1024892 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1499946 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 0.6660. Min Range: -0.6660

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1567477 (Python Code)

Max Activating Token Index: 84