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

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

Neuron 4036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1971. Min Act: -0.0000

Data Index: 272758 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1876. Min Act: -0.0000

Data Index: 556366 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1683. Min Act: -0.0000

Data Index: 947244 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1321. Min Act: -0.0000

Data Index: 19936 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1208. Min Act: -0.0000

Data Index: 304065 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0862. Min Act: -0.0000

Data Index: 911456 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1478566 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1089022 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0794. Min Act: -0.0000

Data Index: 670591 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0935. Min Act: -0.0000

Data Index: 806186 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0770. Min Act: -0.0000

Data Index: 150952 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0646. Min Act: -0.0000

Data Index: 911901 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1073589 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0671. Min Act: -0.0000

Data Index: 798949 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0555. Min Act: -0.0000

Data Index: 847290 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0683. Min Act: -0.0000

Data Index: 710365 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0673. Min Act: -0.0000

Data Index: 119004 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0649. Min Act: -0.0000

Data Index: 589551 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0660. Min Act: -0.0000

Data Index: 950994 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.0636. Min Act: -0.0000

Data Index: 819675 (C4 (Web Text))

Max Activating Token Index: 937