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

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

Neuron 3125 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4915. Min Act: -0.0000

Data Index: 646857 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4688. Min Act: -0.0000

Data Index: 24069 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3941. Min Act: -0.0000

Data Index: 835531 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.8431. Min Act: -0.0000

Data Index: 1176227 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.5561. Min Act: -0.0000

Data Index: 561735 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3955. Min Act: -0.0000

Data Index: 857404 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1028274 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.3455. Min Act: -0.0000

Data Index: 440982 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4752. Min Act: -0.0000

Data Index: 240700 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4166. Min Act: -0.0000

Data Index: 426480 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.4225. Min Act: -0.0000

Data Index: 968484 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.1440. Min Act: -0.0000

Data Index: 397151 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.1777. Min Act: -0.0000

Data Index: 691139 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1324514 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.5735. Min Act: -0.0000

Data Index: 292030 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.0742. Min Act: -0.0000

Data Index: 403575 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.1340. Min Act: -0.0000

Data Index: 247661 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1291768 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.2552. Min Act: -0.0000

Data Index: 612215 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 1.8431. Min Range: -1.8431

Max Act: 1.0145. Min Act: -0.0000

Data Index: 639788 (C4 (Web Text))

Max Activating Token Index: 299