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

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

Neuron 6015 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: 2.6110. Min Range: -2.6110

Max Act: 2.6110. Min Act: -0.0000

Data Index: 780176 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.3704. Min Act: -0.0000

Data Index: 1531883 (Python Code)

Max Activating Token Index: 406

Text #2

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.2913. Min Act: -0.0000

Data Index: 351604 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.2637. Min Act: -0.0000

Data Index: 404735 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.3393. Min Act: -0.0000

Data Index: 782751 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.1026. Min Act: -0.0000

Data Index: 729006 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.2103. Min Act: -0.0000

Data Index: 268440 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.1633. Min Act: -0.0000

Data Index: 524867 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.1468. Min Act: -0.0000

Data Index: 110737 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.6110. Min Range: -2.6110

Max Act: 1.9152. Min Act: -0.0000

Data Index: 24718 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.1124. Min Act: -0.0000

Data Index: 934290 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0814. Min Act: -0.0000

Data Index: 1351006 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0846. Min Act: -0.0000

Data Index: 838475 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 2.6110. Min Range: -2.6110

Max Act: 1.9312. Min Act: -0.0000

Data Index: 1575604 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0370. Min Act: -0.0000

Data Index: 997762 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0291. Min Act: -0.0000

Data Index: 507097 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.1218. Min Act: -0.0000

Data Index: 740591 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1160070 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 2.6110. Min Range: -2.6110

Max Act: 2.0109. Min Act: -0.0000

Data Index: 1330294 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 2.6110. Min Range: -2.6110

Max Act: 1.9923. Min Act: -0.0000

Data Index: 289845 (C4 (Web Text))

Max Activating Token Index: 1007