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

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

Neuron 581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1238346 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7309. Min Act: -0.0000

Data Index: 978391 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7574. Min Act: -0.0000

Data Index: 946104 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7745. Min Act: -0.0000

Data Index: 573105 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1194246 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7621. Min Act: -0.0000

Data Index: 686824 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6939. Min Act: -0.0000

Data Index: 201148 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6667. Min Act: -0.0000

Data Index: 299952 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6955. Min Act: -0.0000

Data Index: 535477 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6044. Min Act: -0.0000

Data Index: 700528 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6151. Min Act: -0.0000

Data Index: 965680 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6267. Min Act: -0.0000

Data Index: 95650 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1079230 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6836. Min Act: -0.0000

Data Index: 262803 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6107. Min Act: -0.0000

Data Index: 438601 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5936. Min Act: -0.0000

Data Index: 713216 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6032. Min Act: -0.0000

Data Index: 150161 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6141. Min Act: -0.0000

Data Index: 670805 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6342. Min Act: -0.0000

Data Index: 748172 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5570. Min Act: -0.0000

Data Index: 37476 (C4 (Web Text))

Max Activating Token Index: 954