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

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

Neuron 1699 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.5102. Min Act: -0.0001

Data Index: 855941 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.3560. Min Act: -0.0001

Data Index: 313913 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.3495. Min Act: -0.0001

Data Index: 508119 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.3264. Min Act: -0.0001

Data Index: 438298 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.3104. Min Act: -0.0001

Data Index: 625214 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.3851. Min Act: -0.0001

Data Index: 104743 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.2841. Min Act: -0.0001

Data Index: 1120569 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1907. Min Act: -0.0001

Data Index: 1205625 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.2601. Min Act: -0.0001

Data Index: 909504 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.2195. Min Act: -0.0001

Data Index: 801482 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.2233. Min Act: -0.0001

Data Index: 1036735 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.2601. Min Act: -0.0001

Data Index: 898250 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1170. Min Act: -0.0001

Data Index: 1087951 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1770. Min Act: -0.0001

Data Index: 973958 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1057411 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1565. Min Act: -0.0001

Data Index: 945387 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1930. Min Act: -0.0001

Data Index: 1097287 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1590. Min Act: -0.0001

Data Index: 242994 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1785. Min Act: -0.0001

Data Index: 129556 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.5102. Min Range: -1.5102

Max Act: 1.1217. Min Act: -0.0001

Data Index: 961644 (C4 (Web Text))

Max Activating Token Index: 330