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

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

Neuron 3844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4769. Min Act: -0.0000

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4152. Min Act: -0.0000

Data Index: 844660 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3815. Min Act: -0.0000

Data Index: 27578 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3820. Min Act: -0.0000

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3638. Min Act: -0.0000

Data Index: 930045 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3569. Min Act: -0.0000

Data Index: 762340 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4093. Min Act: -0.0000

Data Index: 665686 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3954. Min Act: -0.0000

Data Index: 977344 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3599. Min Act: -0.0000

Data Index: 422084 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1061573 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1023918 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3834. Min Act: -0.0000

Data Index: 431140 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3658. Min Act: -0.0000

Data Index: 60314 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3825. Min Act: -0.0000

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1334025 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3662. Min Act: -0.0000

Data Index: 854352 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3712. Min Act: -0.0000

Data Index: 613479 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1357501 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3619. Min Act: -0.0000

Data Index: 168740 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1041508 (C4 (Web Text))

Max Activating Token Index: 67