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

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

Neuron 1194 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.9541. Min Act: -0.0000

Data Index: 168647 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.5659. Min Act: -0.0000

Data Index: 953917 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.5202. Min Act: -0.0000

Data Index: 739510 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1247958 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4645. Min Act: -0.0000

Data Index: 973954 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4808. Min Act: -0.0000

Data Index: 351229 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4679. Min Act: -0.0000

Data Index: 311222 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4467. Min Act: -0.0000

Data Index: 67591 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1020849 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1175980 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1820 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4334. Min Act: -0.0000

Data Index: 621061 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4417. Min Act: -0.0000

Data Index: 418517 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1077657 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4593. Min Act: -0.0001

Data Index: 248156 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4255. Min Act: -0.0000

Data Index: 830492 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1175841 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4219. Min Act: -0.0000

Data Index: 289314 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4040. Min Act: -0.0000

Data Index: 882989 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1151983 (C4 (Web Text))

Max Activating Token Index: 906