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

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

Neuron 3993 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2601. Min Range: -1.2601

Max Act: 1.2601. Min Act: 0.0000

Data Index: 744326 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1048874 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.9719. Min Act: -0.0000

Data Index: 552902 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.9568. Min Act: -0.0000

Data Index: 417350 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8629. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1115123 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8833. Min Act: -0.0000

Data Index: 513735 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8772. Min Act: -0.0000

Data Index: 223495 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.8129. Min Act: -0.0000

Data Index: 893733 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7995. Min Act: -0.0000

Data Index: 720018 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7865. Min Act: -0.0000

Data Index: 522795 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7789. Min Act: 0.0000

Data Index: 521975 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7711. Min Act: -0.0000

Data Index: 121836 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7471. Min Act: -0.0000

Data Index: 351840 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7492. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7377. Min Act: -0.0000

Data Index: 196887 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7286. Min Act: -0.0000

Data Index: 687729 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7284. Min Act: 0.0000

Data Index: 16745 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.2601. Min Range: -1.2601

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1283755 (C4 (Web Text))

Max Activating Token Index: 898