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

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

Neuron 3491 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.7416. Min Act: -0.0000

Data Index: 709176 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.6427. Min Act: -0.0000

Data Index: 1035159 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.4910. Min Act: -0.0000

Data Index: 12982 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.5272. Min Act: -0.0000

Data Index: 1141520 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1100305 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3802. Min Act: -0.0000

Data Index: 1241743 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.1952. Min Act: -0.0000

Data Index: 344792 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3949. Min Act: -0.0000

Data Index: 1043544 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.4834. Min Act: -0.0000

Data Index: 935451 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3538. Min Act: -0.0000

Data Index: 847462 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3988. Min Act: -0.0000

Data Index: 117020 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3220. Min Act: -0.0000

Data Index: 243522 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.3545. Min Act: -0.0000

Data Index: 600758 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.2087. Min Act: -0.0000

Data Index: 821648 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.1164. Min Act: -0.0000

Data Index: 73339 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.2255. Min Act: -0.0000

Data Index: 631843 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.1063. Min Act: -0.0000

Data Index: 488086 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.0964. Min Act: -0.0000

Data Index: 68781 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 2.7416. Min Range: -2.7416

Max Act: 2.1984. Min Act: -0.0000

Data Index: 197833 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.7416. Min Range: -2.7416

Max Act: 1.9870. Min Act: -0.0000

Data Index: 499799 (C4 (Web Text))

Max Activating Token Index: 45