Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9835. Min Act: -0.0000

Data Index: 643063 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.7325. Min Act: -0.0000

Data Index: 482198 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9021. Min Act: -0.0000

Data Index: 504488 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6809. Min Act: -0.0000

Data Index: 236356 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6510. Min Act: -0.0000

Data Index: 1221453 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6529. Min Act: -0.0000

Data Index: 113925 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6140. Min Act: -0.0000

Data Index: 463585 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5102. Min Act: -0.0000

Data Index: 663300 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6680. Min Act: -0.0000

Data Index: 295841 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4527. Min Act: -0.0000

Data Index: 519332 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6223. Min Act: -0.0000

Data Index: 446676 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5283. Min Act: -0.0000

Data Index: 328895 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5904. Min Act: -0.0000

Data Index: 372451 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3184. Min Act: -0.0000

Data Index: 591666 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4839. Min Act: -0.0000

Data Index: 339795 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1021867 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3832. Min Act: -0.0000

Data Index: 166173 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3378. Min Act: -0.0000

Data Index: 399649 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4926. Min Act: -0.0000

Data Index: 409545 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4000. Min Act: -0.0000

Data Index: 885688 (C4 (Web Text))

Max Activating Token Index: 200