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

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

Neuron 5719 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.5527. Min Act: -0.0000

Data Index: 241865 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1130666 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.5038. Min Act: -0.0000

Data Index: 919291 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4761. Min Act: -0.0000

Data Index: 91897 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4617. Min Act: -0.0000

Data Index: 995989 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4616. Min Act: 0.0000

Data Index: 46808 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4547. Min Act: -0.0000

Data Index: 484086 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4574. Min Act: -0.0000

Data Index: 946961 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4659. Min Act: -0.0000

Data Index: 91007 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1139828 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4446. Min Act: -0.0000

Data Index: 932745 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4355. Min Act: -0.0000

Data Index: 287952 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4322. Min Act: -0.0000

Data Index: 583699 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4406. Min Act: -0.0000

Data Index: 710327 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4270. Min Act: -0.0000

Data Index: 430983 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.3970. Min Act: -0.0000

Data Index: 873010 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4194. Min Act: -0.0000

Data Index: 92595 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4185. Min Act: -0.0000

Data Index: 734221 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4032. Min Act: -0.0000

Data Index: 819999 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.5527. Min Range: -0.5527

Max Act: 0.4289. Min Act: 0.0000

Data Index: 594038 (C4 (Web Text))

Max Activating Token Index: 500