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

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

Neuron 2606 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: 1.9574. Min Range: -1.9574

Max Act: 1.9574. Min Act: -0.0000

Data Index: 874011 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4832. Min Act: -0.0000

Data Index: 390152 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1321037 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1250528 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3952. Min Act: -0.0000

Data Index: 356727 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1042769 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1025374 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4058. Min Act: -0.0000

Data Index: 95605 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3214. Min Act: -0.0000

Data Index: 291870 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2880. Min Act: -0.0000

Data Index: 425472 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3549. Min Act: -0.0000

Data Index: 454590 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3170. Min Act: -0.0000

Data Index: 857846 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3415. Min Act: -0.0000

Data Index: 985211 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2465. Min Act: -0.0000

Data Index: 375581 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2688. Min Act: -0.0000

Data Index: 28557 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2496. Min Act: -0.0000

Data Index: 112411 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2840. Min Act: -0.0000

Data Index: 547621 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.1715. Min Act: -0.0000

Data Index: 676528 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.1695. Min Act: -0.0000

Data Index: 616387 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.1327. Min Act: -0.0000

Data Index: 146657 (C4 (Web Text))

Max Activating Token Index: 935