Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2667 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1438. Min Act: -0.0001

Data Index: 778296 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1051. Min Act: -0.0001

Data Index: 633226 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1098. Min Act: -0.0000

Data Index: 254599 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1313278 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0974. Min Act: -0.0001

Data Index: 390074 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0823. Min Act: -0.0001

Data Index: 110149 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0849. Min Act: -0.0001

Data Index: 90484 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0895. Min Act: -0.0001

Data Index: 431896 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0870. Min Act: -0.0001

Data Index: 744788 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1020. Min Act: -0.0001

Data Index: 484247 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0879. Min Act: -0.0001

Data Index: 657527 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1272277 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0925. Min Act: -0.0001

Data Index: 479067 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1270489 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1330233 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0707. Min Act: -0.0001

Data Index: 363769 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0769. Min Act: -0.0001

Data Index: 823155 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0702. Min Act: -0.0000

Data Index: 120263 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0799. Min Act: -0.0001

Data Index: 116977 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0796. Min Act: -0.0001

Data Index: 612953 (C4 (Web Text))

Max Activating Token Index: 508