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

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

Neuron 1943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1057128 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4757. Min Act: -0.0000

Data Index: 634008 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4869. Min Act: -0.0000

Data Index: 7590 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4467. Min Act: -0.0000

Data Index: 413717 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1397155 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4372. Min Act: -0.0001

Data Index: 191929 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4339. Min Act: -0.0001

Data Index: 491226 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4324. Min Act: -0.0000

Data Index: 368965 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4332. Min Act: -0.0000

Data Index: 397658 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1121290 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3840. Min Act: -0.0000

Data Index: 494064 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1026393 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3811. Min Act: -0.0000

Data Index: 423782 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1016060 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3736. Min Act: -0.0001

Data Index: 221208 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.4099. Min Act: -0.0000

Data Index: 415862 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3910. Min Act: -0.0000

Data Index: 233887 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3827. Min Act: -0.0000

Data Index: 400018 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3822. Min Act: -0.0000

Data Index: 969291 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.4869. Min Range: -0.4869

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1416937 (Python Code)

Max Activating Token Index: 74