Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0003

Data Index: 538884 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0815. Min Act: -0.0003

Data Index: 448141 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0822. Min Act: -0.0003

Data Index: 257152 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0776. Min Act: -0.0004

Data Index: 345763 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0748. Min Act: -0.0003

Data Index: 328717 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1476265 (Python Code)

Max Activating Token Index: 917

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0745. Min Act: -0.0003

Data Index: 327173 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0760. Min Act: -0.0003

Data Index: 83938 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1259465 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0738. Min Act: -0.0003

Data Index: 79335 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0728. Min Act: -0.0003

Data Index: 759594 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1326764 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1066479 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0716. Min Act: -0.0003

Data Index: 107483 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0693. Min Act: -0.0003

Data Index: 536937 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1262954 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1147482 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0707. Min Act: -0.0003

Data Index: 842586 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0682. Min Act: -0.0004

Data Index: 544839 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0661. Min Act: -0.0004

Data Index: 1220928 (C4 (Web Text))

Max Activating Token Index: 852