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

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

Neuron 3089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.7508. Min Act: -0.0000

Data Index: 87646 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5871. Min Act: -0.0000

Data Index: 998834 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6360. Min Act: -0.0000

Data Index: 590440 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5309. Min Act: -0.0000

Data Index: 186930 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6324. Min Act: -0.0000

Data Index: 228864 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4779. Min Act: -0.0000

Data Index: 803820 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5549. Min Act: -0.0000

Data Index: 344776 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1162711 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5664. Min Act: -0.0000

Data Index: 360544 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6250. Min Act: -0.0000

Data Index: 535234 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5471. Min Act: -0.0000

Data Index: 819832 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5457. Min Act: -0.0000

Data Index: 918292 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5442. Min Act: -0.0000

Data Index: 994142 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1270759 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5416. Min Act: -0.0000

Data Index: 27283 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5240. Min Act: -0.0000

Data Index: 415746 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1120384 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5025. Min Act: -0.0000

Data Index: 828115 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4953. Min Act: -0.0001

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4900. Min Act: -0.0000

Data Index: 71182 (C4 (Web Text))

Max Activating Token Index: 108