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

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

Neuron 3333 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.7814. Min Act: -0.0001

Data Index: 568272 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6495. Min Act: -0.0001

Data Index: 1174509 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6028. Min Act: -0.0001

Data Index: 916475 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.6538. Min Act: -0.0001

Data Index: 848147 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5844. Min Act: -0.0001

Data Index: 281520 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5886. Min Act: -0.0001

Data Index: 1006492 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5471. Min Act: -0.0001

Data Index: 809704 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1073452 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5148. Min Act: -0.0001

Data Index: 527591 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5779. Min Act: -0.0001

Data Index: 1181874 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1038940 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5722. Min Act: -0.0001

Data Index: 602771 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5338. Min Act: -0.0001

Data Index: 416989 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5567. Min Act: -0.0001

Data Index: 919496 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5373. Min Act: -0.0001

Data Index: 1268773 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5271. Min Act: -0.0001

Data Index: 1114506 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1334275 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5498. Min Act: -0.0001

Data Index: 871302 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5282. Min Act: -0.0001

Data Index: 545561 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.7814. Min Range: -0.7814

Max Act: 0.5316. Min Act: -0.0001

Data Index: 289040 (C4 (Web Text))

Max Activating Token Index: 234