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

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

Neuron 600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.2672. Min Act: -0.0000

Data Index: 486330 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1309834 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.1054. Min Act: -0.0000

Data Index: 489500 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1169157 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9864. Min Act: -0.0000

Data Index: 519630 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0569. Min Act: -0.0000

Data Index: 191616 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1266806 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0581. Min Act: -0.0000

Data Index: 88435 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1078735 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0572. Min Act: -0.0000

Data Index: 28929 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0471. Min Act: -0.0000

Data Index: 376509 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0108. Min Act: -0.0000

Data Index: 95983 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.1019. Min Act: -0.0000

Data Index: 721471 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9931. Min Act: -0.0000

Data Index: 149172 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9537. Min Act: -0.0000

Data Index: 801342 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.1102. Min Act: -0.0000

Data Index: 357058 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9673. Min Act: -0.0000

Data Index: 720428 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.2672. Min Range: -1.2672

Max Act: 0.9944. Min Act: -0.0000

Data Index: 267516 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0194. Min Act: -0.0000

Data Index: 520445 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.2672. Min Range: -1.2672

Max Act: 1.0220. Min Act: -0.0000

Data Index: 52225 (C4 (Web Text))

Max Activating Token Index: 816