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

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

Neuron 3825 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: 1.0569. Min Range: -1.0569

Max Act: 1.0569. Min Act: -0.0002

Data Index: 700296 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.0569. Min Range: -1.0569

Max Act: 1.0380. Min Act: -0.0002

Data Index: 911067 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9802. Min Act: -0.0002

Data Index: 1016945 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9575. Min Act: -0.0002

Data Index: 469476 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9498. Min Act: -0.0002

Data Index: 427838 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9892. Min Act: -0.0002

Data Index: 1058021 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9256. Min Act: -0.0002

Data Index: 884860 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.9279. Min Act: -0.0002

Data Index: 431947 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8518. Min Act: -0.0002

Data Index: 268514 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8207. Min Act: -0.0002

Data Index: 1321277 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8812. Min Act: -0.0002

Data Index: 387886 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8461. Min Act: -0.0002

Data Index: 1023705 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8660. Min Act: -0.0002

Data Index: 421788 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8656. Min Act: -0.0002

Data Index: 1343437 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8586. Min Act: -0.0002

Data Index: 979898 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8748. Min Act: -0.0002

Data Index: 1118862 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8777. Min Act: -0.0002

Data Index: 1303444 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8360. Min Act: -0.0002

Data Index: 661466 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8107. Min Act: -0.0002

Data Index: 5315 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.0569. Min Range: -1.0569

Max Act: 0.8109. Min Act: -0.0002

Data Index: 470970 (C4 (Web Text))

Max Activating Token Index: 497