Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 636 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0000

Data Index: 789341 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1189134 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0685. Min Act: -0.0000

Data Index: 815635 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1210259 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9405. Min Act: -0.0000

Data Index: 453975 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9250. Min Act: -0.0000

Data Index: 993871 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0087. Min Act: -0.0000

Data Index: 824007 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1163373 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9125. Min Act: -0.0000

Data Index: 935567 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9706. Min Act: -0.0000

Data Index: 11031 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9304. Min Act: -0.0000

Data Index: 723516 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9392. Min Act: -0.0000

Data Index: 587854 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8629. Min Act: -0.0000

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8782. Min Act: -0.0000

Data Index: 209086 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9074. Min Act: -0.0000

Data Index: 1211578 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8820. Min Act: -0.0000

Data Index: 450677 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8832. Min Act: -0.0000

Data Index: 563906 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9024. Min Act: -0.0000

Data Index: 468120 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1162642 (C4 (Web Text))

Max Activating Token Index: 738