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

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

Neuron 3843 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.6596. Min Act: -0.0000

Data Index: 218618 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.9354. Min Act: -0.0000

Data Index: 1229002 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.7493. Min Act: -0.0000

Data Index: 56051 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.5247. Min Act: -0.0000

Data Index: 721377 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.3111. Min Act: -0.0000

Data Index: 543788 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.3100. Min Act: -0.0000

Data Index: 691735 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.1685. Min Act: -0.0000

Data Index: 636838 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.2640. Min Act: -0.0000

Data Index: 1062744 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0533. Min Act: -0.0000

Data Index: 1146696 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.1382. Min Act: -0.0000

Data Index: 1075903 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0896. Min Act: -0.0000

Data Index: 702088 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0697. Min Act: -0.0000

Data Index: 1214217 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 2.9354. Min Range: -2.9354

Max Act: 1.9617. Min Act: -0.0000

Data Index: 356970 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0674. Min Act: -0.0000

Data Index: 847880 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0267. Min Act: -0.0000

Data Index: 750345 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 2.9354. Min Range: -2.9354

Max Act: 2.0261. Min Act: -0.0000

Data Index: 603749 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 2.9354. Min Range: -2.9354

Max Act: 1.9785. Min Act: -0.0000

Data Index: 875130 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.9354. Min Range: -2.9354

Max Act: 1.9775. Min Act: 0.0000

Data Index: 679404 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 2.9354. Min Range: -2.9354

Max Act: 1.9625. Min Act: -0.0000

Data Index: 437261 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 2.9354. Min Range: -2.9354

Max Act: 1.9374. Min Act: -0.0000

Data Index: 600674 (C4 (Web Text))

Max Activating Token Index: 336