Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 21 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1797. Min Range: -1.1797

Max Act: 1.1797. Min Act: -0.0000

Data Index: 912210 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.1797. Min Range: -1.1797

Max Act: 1.1195. Min Act: -0.0000

Data Index: 608045 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.1797. Min Range: -1.1797

Max Act: 1.0940. Min Act: -0.0000

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.1797. Min Range: -1.1797

Max Act: 1.0312. Min Act: -0.0001

Data Index: 988220 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.1797. Min Range: -1.1797

Max Act: 1.0492. Min Act: -0.0001

Data Index: 32559 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1321395 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9620. Min Act: -0.0001

Data Index: 881024 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9917. Min Act: -0.0000

Data Index: 627965 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9025. Min Act: -0.0000

Data Index: 942571 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9391. Min Act: -0.0000

Data Index: 573341 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8795. Min Act: -0.0001

Data Index: 919601 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9327. Min Act: -0.0000

Data Index: 21260 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9020. Min Act: -0.0000

Data Index: 256831 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8771. Min Act: -0.0000

Data Index: 571378 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9193. Min Act: -0.0001

Data Index: 245265 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8609. Min Act: -0.0000

Data Index: 260988 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.9046. Min Act: -0.0001

Data Index: 700111 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8305. Min Act: -0.0000

Data Index: 702454 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1096631 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.1797. Min Range: -1.1797

Max Act: 0.8835. Min Act: -0.0000

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 614