Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4941 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1162057 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.4245. Min Act: -0.0000

Data Index: 83148 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.4005. Min Act: -0.0000

Data Index: 508426 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1209850 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3603. Min Act: -0.0000

Data Index: 790497 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3382. Min Act: -0.0000

Data Index: 34032 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3436. Min Act: -0.0000

Data Index: 873545 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3327. Min Act: -0.0000

Data Index: 534401 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1146906 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2963. Min Act: -0.0000

Data Index: 454889 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2968. Min Act: -0.0000

Data Index: 4944 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1315716 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2573. Min Act: -0.0000

Data Index: 942413 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2915. Min Act: -0.0000

Data Index: 465284 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2848. Min Act: -0.0000

Data Index: 701595 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2930. Min Act: -0.0000

Data Index: 345724 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1160130 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2772. Min Act: -0.0000

Data Index: 833676 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1090908 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.4245. Min Range: -0.4245

Max Act: 0.2683. Min Act: -0.0000

Data Index: 803332 (C4 (Web Text))

Max Activating Token Index: 389