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

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

Neuron 5678 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1290850 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1080120 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1043. Min Act: -0.0001

Data Index: 526425 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0881. Min Act: -0.0001

Data Index: 976023 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1118921 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0952. Min Act: -0.0001

Data Index: 991441 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0741. Min Act: -0.0001

Data Index: 419931 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0934. Min Act: -0.0001

Data Index: 607075 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0891. Min Act: -0.0001

Data Index: 633022 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1205433 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0914. Min Act: -0.0002

Data Index: 71046 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0829. Min Act: -0.0001

Data Index: 904876 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0887. Min Act: -0.0001

Data Index: 392674 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0864. Min Act: -0.0001

Data Index: 832803 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0795. Min Act: -0.0001

Data Index: 947872 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0892. Min Act: -0.0001

Data Index: 25997 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1204976 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1169631 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0850. Min Act: -0.0001

Data Index: 610515 (C4 (Web Text))

Max Activating Token Index: 238