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

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

Neuron 5943 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.7794. Min Act: -0.0000

Data Index: 1219413 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1270096 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.6189. Min Act: -0.0000

Data Index: 979437 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5499. Min Act: -0.0000

Data Index: 420822 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.5044. Min Act: -0.0000

Data Index: 476613 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.4430. Min Act: -0.0000

Data Index: 338398 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1358312 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1003421 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3316. Min Act: -0.0000

Data Index: 334415 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1232823 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.3199. Min Act: -0.0000

Data Index: 433606 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2466. Min Act: -0.0000

Data Index: 38765 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1162434 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2755. Min Act: -0.0000

Data Index: 513357 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2067. Min Act: -0.0000

Data Index: 1264382 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2749. Min Act: -0.0000

Data Index: 565309 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2401. Min Act: -0.0000

Data Index: 310530 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2483. Min Act: -0.0000

Data Index: 536619 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1181589 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.7794. Min Range: -1.7794

Max Act: 1.1142. Min Act: -0.0000

Data Index: 359702 (C4 (Web Text))

Max Activating Token Index: 985