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

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

Neuron 2401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7966. Min Act: -0.0000

Data Index: 223132 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.7772. Min Act: -0.0000

Data Index: 183715 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1294972 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1436268 (Python Code)

Max Activating Token Index: 720

Text #4

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6234. Min Act: -0.0000

Data Index: 595308 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5907. Min Act: -0.0000

Data Index: 856821 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1249706 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6070. Min Act: -0.0000

Data Index: 68416 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5705. Min Act: -0.0000

Data Index: 273434 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1411352 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1604785 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1257795 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5898. Min Act: -0.0000

Data Index: 548021 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1278883 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5742. Min Act: -0.0000

Data Index: 69758 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1274509 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5294. Min Act: -0.0000

Data Index: 709774 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.4581. Min Act: -0.0000

Data Index: 818540 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.6032. Min Act: -0.0000

Data Index: 132147 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.7966. Min Range: -0.7966

Max Act: 0.5241. Min Act: -0.0000

Data Index: 651450 (C4 (Web Text))

Max Activating Token Index: 746