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

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

Neuron 2024 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.9794. Min Act: -0.0001

Data Index: 645558 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.9575. Min Act: -0.0001

Data Index: 776247 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.7398. Min Act: -0.0001

Data Index: 496580 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1293596 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.5946. Min Act: -0.0001

Data Index: 1061376 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.7651. Min Act: -0.0001

Data Index: 1335595 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.8600. Min Act: -0.0001

Data Index: 625858 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.6432. Min Act: -0.0001

Data Index: 920123 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.6217. Min Act: -0.0001

Data Index: 34863 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.7000. Min Act: -0.0001

Data Index: 1044498 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.4978. Min Act: -0.0001

Data Index: 72112 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.6230. Min Act: -0.0000

Data Index: 561791 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.5728. Min Act: -0.0001

Data Index: 1257200 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1241607 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.6839. Min Act: -0.0001

Data Index: 1210440 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.5654. Min Act: -0.0001

Data Index: 1209636 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.4992. Min Act: -0.0000

Data Index: 299249 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.3391. Min Act: -0.0001

Data Index: 233425 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.4459. Min Act: -0.0001

Data Index: 368760 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.9794. Min Range: -1.9794

Max Act: 1.4458. Min Act: -0.0000

Data Index: 924257 (C4 (Web Text))

Max Activating Token Index: 467