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

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

Neuron 4608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.7906. Min Act: -0.0001

Data Index: 721096 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.9416. Min Act: -0.0001

Data Index: 1034566 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.7156. Min Act: -0.0001

Data Index: 576047 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.6328. Min Act: -0.0001

Data Index: 677576 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.6025. Min Act: -0.0001

Data Index: 251140 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.5773. Min Act: -0.0001

Data Index: 927220 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.6070. Min Act: -0.0001

Data Index: 727777 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.3091. Min Act: -0.0001

Data Index: 771829 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.5670. Min Act: -0.0001

Data Index: 26509 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.5125. Min Act: -0.0001

Data Index: 385919 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.5698. Min Act: -0.0001

Data Index: 304863 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.3439. Min Act: -0.0001

Data Index: 586075 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.5602. Min Act: -0.0001

Data Index: 621166 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.3780. Min Act: -0.0001

Data Index: 70860 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.4491. Min Act: -0.0001

Data Index: 104794 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.2652. Min Act: -0.0001

Data Index: 1183161 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.2533. Min Act: -0.0001

Data Index: 590702 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.2739. Min Act: -0.0001

Data Index: 329162 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.2760. Min Act: -0.0001

Data Index: 868737 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.9416. Min Range: -1.9416

Max Act: 1.3124. Min Act: -0.0001

Data Index: 1092849 (C4 (Web Text))

Max Activating Token Index: 6