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

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

Neuron 423 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5509. Min Act: -0.0001

Data Index: 494201 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5500. Min Act: -0.0001

Data Index: 1059473 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1116457 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5032. Min Act: -0.0001

Data Index: 925940 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5085. Min Act: -0.0001

Data Index: 594148 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5006. Min Act: -0.0001

Data Index: 106850 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4663. Min Act: -0.0001

Data Index: 119937 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4617. Min Act: -0.0001

Data Index: 545743 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4843. Min Act: -0.0001

Data Index: 886079 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.5042. Min Act: -0.0001

Data Index: 1205060 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4782. Min Act: -0.0001

Data Index: 1282822 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4666. Min Act: -0.0001

Data Index: 335344 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4794. Min Act: -0.0001

Data Index: 837599 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4875. Min Act: -0.0001

Data Index: 206825 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4538. Min Act: -0.0001

Data Index: 610104 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4943. Min Act: -0.0001

Data Index: 471989 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4045. Min Act: -0.0001

Data Index: 1224652 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1644176 (Python Code)

Max Activating Token Index: 711

Text #18

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4326. Min Act: -0.0001

Data Index: 979176 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.5509. Min Range: -0.5509

Max Act: 0.4441. Min Act: -0.0001

Data Index: 85271 (C4 (Web Text))

Max Activating Token Index: 38