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

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

Neuron 338 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1167270 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1023871 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0802. Min Act: -0.0000

Data Index: 494385 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0788. Min Act: -0.0000

Data Index: 887479 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0784. Min Act: -0.0000

Data Index: 535908 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1185817 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0718. Min Act: -0.0000

Data Index: 982084 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0704. Min Act: -0.0000

Data Index: 827338 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1072313 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0684. Min Act: -0.0000

Data Index: 394389 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0674. Min Act: -0.0000

Data Index: 189123 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1361451 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0627. Min Act: -0.0000

Data Index: 630823 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0687. Min Act: -0.0000

Data Index: 657023 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0699. Min Act: -0.0000

Data Index: 765930 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0580. Min Act: 0.0000

Data Index: 945190 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0660. Min Act: -0.0000

Data Index: 454577 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1592286 (Python Code)

Max Activating Token Index: 404

Text #18

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0703. Min Act: -0.0000

Data Index: 106694 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0975. Min Range: -0.0975

Max Act: 0.0631. Min Act: -0.0000

Data Index: 946345 (C4 (Web Text))

Max Activating Token Index: 528