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

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

Neuron 733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1530. Min Range: -1.1530

Max Act: 1.1530. Min Act: -0.0000

Data Index: 880958 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1260663 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.9214. Min Act: -0.0000

Data Index: 403719 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1083074 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1038171 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8457. Min Act: -0.0000

Data Index: 756129 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1264594 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8173. Min Act: -0.0000

Data Index: 910440 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8087. Min Act: -0.0000

Data Index: 518021 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1025231 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8028. Min Act: -0.0000

Data Index: 563872 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.7687. Min Act: -0.0000

Data Index: 308651 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1010335 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1022945 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.7189. Min Act: -0.0000

Data Index: 473986 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8573. Min Act: -0.0000

Data Index: 25210 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8265. Min Act: -0.0000

Data Index: 418332 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.7460. Min Act: -0.0000

Data Index: 816974 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1334709 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.1530. Min Range: -1.1530

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1131889 (C4 (Web Text))

Max Activating Token Index: 313