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

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

Neuron 1926 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: 1.3903. Min Range: -1.3903

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1312014 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.3903. Min Range: -1.3903

Max Act: 1.3841. Min Act: -0.0000

Data Index: 33413 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.3903. Min Range: -1.3903

Max Act: 1.0092. Min Act: -0.0000

Data Index: 678840 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1296769 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8883. Min Act: -0.0000

Data Index: 5886 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8265. Min Act: -0.0000

Data Index: 776805 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1326842 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8724. Min Act: -0.0000

Data Index: 50747 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7562. Min Act: -0.0000

Data Index: 794119 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.9092. Min Act: -0.0000

Data Index: 417659 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8426. Min Act: -0.0000

Data Index: 463398 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1225118 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.8032. Min Act: -0.0000

Data Index: 989971 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.6321. Min Act: -0.0000

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1108805 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1339997 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.6958. Min Act: -0.0000

Data Index: 412210 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.6944. Min Act: -0.0000

Data Index: 579059 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.7013. Min Act: -0.0000

Data Index: 343582 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.3903. Min Range: -1.3903

Max Act: 0.6513. Min Act: -0.0000

Data Index: 889016 (C4 (Web Text))

Max Activating Token Index: 658