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

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

Neuron 4034 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: 0.5666. Min Range: -0.5666

Max Act: 0.5666. Min Act: -0.0001

Data Index: 874617 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4900. Min Act: -0.0000

Data Index: 327512 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4446. Min Act: -0.0001

Data Index: 432681 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4968. Min Act: -0.0000

Data Index: 393129 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4761. Min Act: -0.0001

Data Index: 973044 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4884. Min Act: -0.0001

Data Index: 146275 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.5030. Min Act: -0.0001

Data Index: 23255 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4834. Min Act: -0.0001

Data Index: 991940 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1133904 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4801. Min Act: -0.0000

Data Index: 14117 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1111034 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4564. Min Act: -0.0000

Data Index: 381386 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4198. Min Act: -0.0001

Data Index: 365558 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1219790 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4187. Min Act: -0.0001

Data Index: 922135 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4235. Min Act: -0.0000

Data Index: 421681 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4235. Min Act: -0.0001

Data Index: 101028 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1043597 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.3798. Min Act: -0.0001

Data Index: 448944 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.5666. Min Range: -0.5666

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1312522 (C4 (Web Text))

Max Activating Token Index: 126