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

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

Neuron 2462 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: 1.6609. Min Range: -1.6609

Max Act: 1.5906. Min Act: -0.0001

Data Index: 1025812 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.6609. Min Act: -0.0001

Data Index: 179698 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.4841. Min Act: -0.0001

Data Index: 1289567 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.3605. Min Act: -0.0001

Data Index: 623047 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.5378. Min Act: -0.0001

Data Index: 399655 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.6099. Min Act: -0.0001

Data Index: 626492 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.4472. Min Act: -0.0001

Data Index: 1275315 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.4899. Min Act: -0.0001

Data Index: 399483 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.3869. Min Act: -0.0001

Data Index: 1075240 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.3459. Min Act: -0.0001

Data Index: 701539 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2852. Min Act: -0.0001

Data Index: 914409 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2981. Min Act: -0.0001

Data Index: 723725 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2723. Min Act: -0.0001

Data Index: 1272432 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2568. Min Act: -0.0001

Data Index: 855813 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2914. Min Act: -0.0001

Data Index: 889266 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.3722. Min Act: -0.0001

Data Index: 1210256 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.2110. Min Act: -0.0001

Data Index: 1299886 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.1505. Min Act: -0.0001

Data Index: 1150678 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.1770. Min Act: -0.0001

Data Index: 424975 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.6609. Min Range: -1.6609

Max Act: 1.1389. Min Act: -0.0001

Data Index: 890691 (C4 (Web Text))

Max Activating Token Index: 577