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

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

Neuron 536 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1702. Min Range: -2.1702

Max Act: 2.1621. Min Act: -0.0000

Data Index: 486363 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 2.1702. Min Range: -2.1702

Max Act: 2.1702. Min Act: -0.0000

Data Index: 891823 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 2.1702. Min Range: -2.1702

Max Act: 2.1498. Min Act: -0.0000

Data Index: 1250767 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 2.1702. Min Range: -2.1702

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1083561 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 2.1702. Min Range: -2.1702

Max Act: 2.1588. Min Act: -0.0000

Data Index: 568000 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.9864. Min Act: -0.0000

Data Index: 1056336 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.9642. Min Act: -0.0000

Data Index: 553457 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.9134. Min Act: -0.0000

Data Index: 128575 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.9075. Min Act: -0.0000

Data Index: 513034 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7810. Min Act: -0.0000

Data Index: 460664 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.8516. Min Act: -0.0000

Data Index: 226747 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7196. Min Act: -0.0000

Data Index: 846493 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.9064. Min Act: -0.0000

Data Index: 916818 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7963. Min Act: -0.0000

Data Index: 1353130 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.8172. Min Act: -0.0000

Data Index: 78087 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.8000. Min Act: -0.0000

Data Index: 210003 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7853. Min Act: -0.0000

Data Index: 707614 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7856. Min Act: -0.0000

Data Index: 588138 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.7629. Min Act: -0.0000

Data Index: 1207066 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.1702. Min Range: -2.1702

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1059632 (C4 (Web Text))

Max Activating Token Index: 307