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

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

Neuron 2650 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7246. Min Act: -0.0000

Data Index: 650468 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.9411. Min Act: -0.0000

Data Index: 294569 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7177. Min Act: -0.0000

Data Index: 680430 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.6907. Min Act: -0.0000

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.8635. Min Act: -0.0000

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.5690. Min Act: -0.0000

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.6549. Min Act: -0.0000

Data Index: 1344094 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.4623. Min Act: -0.0000

Data Index: 1285991 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0362. Min Act: -0.0000

Data Index: 340305 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7207. Min Act: -0.0000

Data Index: 622151 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.3416. Min Act: -0.0000

Data Index: 141201 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1874. Min Act: -0.0000

Data Index: 860615 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1341. Min Act: -0.0000

Data Index: 1015769 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1777. Min Act: -0.0000

Data Index: 1103802 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1563. Min Act: -0.0000

Data Index: 965882 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1625. Min Act: -0.0000

Data Index: 837268 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1590. Min Act: -0.0000

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.9411. Min Range: -3.9411

Max Act: 2.8447. Min Act: -0.0000

Data Index: 818287 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.2590. Min Act: -0.0000

Data Index: 1268507 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0823. Min Act: -0.0000

Data Index: 1047391 (C4 (Web Text))

Max Activating Token Index: 25