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

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

Neuron 2635 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: 4.1100. Min Range: -4.1100

Max Act: 3.9784. Min Act: -0.0000

Data Index: 280437 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 4.1100. Min Range: -4.1100

Max Act: 4.1100. Min Act: -0.0000

Data Index: 1121108 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.6684. Min Act: -0.0000

Data Index: 268123 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.2544. Min Act: -0.0001

Data Index: 108716 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.4049. Min Act: -0.0000

Data Index: 1018638 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.3860. Min Act: -0.0000

Data Index: 338557 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.1470. Min Act: -0.0000

Data Index: 441061 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 4.1100. Min Range: -4.1100

Max Act: 3.0119. Min Act: -0.0000

Data Index: 803171 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.9924. Min Act: -0.0000

Data Index: 113295 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.8207. Min Act: -0.0000

Data Index: 1317256 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.6445. Min Act: -0.0000

Data Index: 980843 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.9013. Min Act: -0.0000

Data Index: 946471 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.7544. Min Act: -0.0000

Data Index: 671881 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.7360. Min Act: -0.0001

Data Index: 1098976 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.9759. Min Act: -0.0000

Data Index: 487600 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.7280. Min Act: -0.0000

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.5784. Min Act: -0.0000

Data Index: 421296 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.5477. Min Act: -0.0000

Data Index: 1046106 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.6793. Min Act: -0.0000

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 4.1100. Min Range: -4.1100

Max Act: 2.6919. Min Act: -0.0000

Data Index: 1048689 (C4 (Web Text))

Max Activating Token Index: 611