Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.4765. Min Act: -0.0000

Data Index: 452050 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.2709. Min Act: -0.0000

Data Index: 403069 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.1200. Min Act: -0.0000

Data Index: 760288 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.1122. Min Act: -0.0000

Data Index: 36500 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.1096. Min Act: -0.0000

Data Index: 807466 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0076. Min Act: -0.0000

Data Index: 241481 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0320. Min Act: -0.0001

Data Index: 1591613 (Python Code)

Max Activating Token Index: 842

Text #7

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1184908 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0147. Min Act: -0.0000

Data Index: 188618 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1216565 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0273. Min Act: -0.0001

Data Index: 1597406 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9911. Min Act: -0.0000

Data Index: 216598 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0426. Min Act: -0.0000

Data Index: 131319 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1345945 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9630. Min Act: -0.0000

Data Index: 11646 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9923. Min Act: -0.0001

Data Index: 934085 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.4765. Min Range: -1.4765

Max Act: 1.0110. Min Act: -0.0001

Data Index: 149701 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1291603 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9534. Min Act: -0.0000

Data Index: 536336 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 1.4765. Min Range: -1.4765

Max Act: 0.9411. Min Act: -0.0001

Data Index: 536209 (C4 (Web Text))

Max Activating Token Index: 546