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

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

Neuron 3899 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: 0.7345. Min Range: -0.7345

Max Act: 0.7345. Min Act: -0.0000

Data Index: 313314 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6896. Min Act: -0.0000

Data Index: 588557 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1256959 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1097730 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1114062 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5504. Min Act: -0.0000

Data Index: 134263 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5579. Min Act: -0.0000

Data Index: 695941 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1136795 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5702. Min Act: -0.0000

Data Index: 692412 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5188. Min Act: -0.0000

Data Index: 875235 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1316967 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.5282. Min Act: -0.0000

Data Index: 543725 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4783. Min Act: -0.0000

Data Index: 451600 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1141675 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4642. Min Act: -0.0000

Data Index: 719298 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1259707 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1050635 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4773. Min Act: -0.0000

Data Index: 725051 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4755. Min Act: -0.0000

Data Index: 987944 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.7345. Min Range: -0.7345

Max Act: 0.4495. Min Act: -0.0000

Data Index: 284976 (C4 (Web Text))

Max Activating Token Index: 101