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

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

Neuron 2715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.8667. Min Act: -0.0000

Data Index: 904059 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.8667. Min Act: -0.0000

Data Index: 535649 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.8667. Min Act: -0.0000

Data Index: 1353079 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.8667. Min Act: -0.0000

Data Index: 411700 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.4578. Min Act: -0.0000

Data Index: 947856 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 1208398 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 496519 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 198122 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 376389 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 541126 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5054. Min Act: -0.0000

Data Index: 486418 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.6764. Min Act: -0.0000

Data Index: 685729 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.6764. Min Act: -0.0000

Data Index: 157931 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.2952. Min Act: -0.0001

Data Index: 266647 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.2952. Min Act: -0.0000

Data Index: 218977 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.3446. Min Act: -0.0000

Data Index: 889591 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.5092. Min Act: -0.0000

Data Index: 570625 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.2814. Min Act: -0.0000

Data Index: 163262 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 5.8667. Min Range: -5.8667

Max Act: 5.1909. Min Act: -0.0000

Data Index: 827001 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 5.8667. Min Range: -5.8667

Max Act: 4.9883. Min Act: -0.0000

Data Index: 1111194 (C4 (Web Text))

Max Activating Token Index: 30