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

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

Neuron 3616 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: 0.9851. Min Range: -0.9851

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1241853 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.8434. Min Act: -0.0001

Data Index: 632820 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7644. Min Act: -0.0000

Data Index: 510783 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7882. Min Act: -0.0000

Data Index: 637514 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.7473. Min Act: -0.0000

Data Index: 225551 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6344. Min Act: -0.0000

Data Index: 182580 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1167593 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6245. Min Act: -0.0001

Data Index: 33307 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1260431 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.6083. Min Act: -0.0000

Data Index: 931792 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5745. Min Act: -0.0000

Data Index: 892071 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5872. Min Act: -0.0000

Data Index: 287105 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5452. Min Act: -0.0000

Data Index: 398356 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5422. Min Act: -0.0001

Data Index: 14229 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5530. Min Act: -0.0001

Data Index: 853923 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5651. Min Act: -0.0000

Data Index: 991543 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1002009 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5413. Min Act: -0.0000

Data Index: 436060 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1096848 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.9851. Min Range: -0.9851

Max Act: 0.4578. Min Act: -0.0000

Data Index: 225444 (C4 (Web Text))

Max Activating Token Index: 767