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

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

Neuron 4366 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.3697. Min Act: -0.0000

Data Index: 603510 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1934. Min Act: -0.0000

Data Index: 605595 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1047240 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8093. Min Act: -0.0000

Data Index: 951525 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7577. Min Act: -0.0000

Data Index: 739655 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1061444 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1481409 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7350. Min Act: -0.0000

Data Index: 497547 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1065886 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6816. Min Act: -0.0000

Data Index: 148048 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1236102 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.5965. Min Act: -0.0000

Data Index: 143635 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6038. Min Act: -0.0000

Data Index: 661233 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.5733. Min Act: -0.0000

Data Index: 207823 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6819. Min Act: -0.0000

Data Index: 633755 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6245. Min Act: -0.0000

Data Index: 823423 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1321664 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.5960. Min Act: -0.0000

Data Index: 285655 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.6073. Min Act: -0.0000

Data Index: 271390 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.4756. Min Act: -0.0000

Data Index: 858001 (C4 (Web Text))

Max Activating Token Index: 796