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

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

Neuron 3380 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5259. Min Act: -0.0000

Data Index: 862264 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1271007 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4195. Min Act: -0.0000

Data Index: 802267 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1092780 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3941. Min Act: -0.0000

Data Index: 947635 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3694. Min Act: -0.0000

Data Index: 861974 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3856. Min Act: -0.0000

Data Index: 346053 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3843. Min Act: -0.0000

Data Index: 526382 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1246000 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1200671 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3927. Min Act: -0.0000

Data Index: 495766 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3616. Min Act: -0.0000

Data Index: 211722 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3928. Min Act: -0.0000

Data Index: 725545 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3380. Min Act: -0.0000

Data Index: 638378 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3570. Min Act: -0.0000

Data Index: 524110 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1290605 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3656. Min Act: -0.0000

Data Index: 87204 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4171. Min Act: -0.0000

Data Index: 812123 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3581. Min Act: -0.0000

Data Index: 739551 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1212594 (C4 (Web Text))

Max Activating Token Index: 209