Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3452 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7386. Min Act: -0.0000

Data Index: 326773 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7594. Min Act: -0.0000

Data Index: 506506 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7141. Min Act: -0.0000

Data Index: 557194 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7112. Min Act: -0.0000

Data Index: 474506 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7340. Min Act: -0.0000

Data Index: 373745 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1210139 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6780. Min Act: -0.0000

Data Index: 924919 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7072. Min Act: -0.0000

Data Index: 434542 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7315. Min Act: -0.0000

Data Index: 525876 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6837. Min Act: -0.0000

Data Index: 138338 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7070. Min Act: -0.0000

Data Index: 477725 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6935. Min Act: -0.0000

Data Index: 464153 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6886. Min Act: -0.0000

Data Index: 396820 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6622. Min Act: -0.0000

Data Index: 450347 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6185. Min Act: -0.0000

Data Index: 721123 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6938. Min Act: -0.0000

Data Index: 540848 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1230218 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6541. Min Act: -0.0000

Data Index: 244450 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6990. Min Act: -0.0000

Data Index: 895730 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.6891. Min Act: -0.0000

Data Index: 25772 (C4 (Web Text))

Max Activating Token Index: 934