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

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

Neuron 3025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0631. Min Range: -7.0631

Max Act: 7.0631. Min Act: -0.0000

Data Index: 167388 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.4002. Min Act: -0.0000

Data Index: 1061710 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.5149. Min Act: -0.0000

Data Index: 840117 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.4935. Min Act: -0.0000

Data Index: 934405 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.4675. Min Act: -0.0000

Data Index: 1059653 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.2334. Min Act: -0.0000

Data Index: 545466 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.1833. Min Act: -0.0000

Data Index: 1053788 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.3044. Min Act: -0.0000

Data Index: 514593 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 7.0631. Min Range: -7.0631

Max Act: 6.0720. Min Act: -0.0000

Data Index: 304541 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.8741. Min Act: -0.0000

Data Index: 450576 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.7907. Min Act: -0.0000

Data Index: 1314060 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.9894. Min Act: -0.0000

Data Index: 1057004 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.5938. Min Act: -0.0000

Data Index: 356553 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.7044. Min Act: -0.0000

Data Index: 983627 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.5229. Min Act: -0.0000

Data Index: 513801 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.5214. Min Act: -0.0000

Data Index: 654008 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.6592. Min Act: -0.0000

Data Index: 394516 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.6236. Min Act: -0.0000

Data Index: 258289 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.5946. Min Act: -0.0000

Data Index: 96886 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 7.0631. Min Range: -7.0631

Max Act: 5.7812. Min Act: -0.0000

Data Index: 307082 (C4 (Web Text))

Max Activating Token Index: 953