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

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

Neuron 4095 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: 1.1808. Min Range: -1.1808

Max Act: 1.1808. Min Act: -0.0000

Data Index: 169101 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0886. Min Act: -0.0000

Data Index: 263149 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1058419 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0301. Min Act: -0.0000

Data Index: 481674 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0055. Min Act: -0.0000

Data Index: 562957 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0463. Min Act: -0.0000

Data Index: 174029 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9251. Min Act: -0.0000

Data Index: 666319 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9913. Min Act: -0.0000

Data Index: 546401 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0153. Min Act: -0.0000

Data Index: 581986 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.1808. Min Range: -1.1808

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1087347 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9731. Min Act: -0.0000

Data Index: 911811 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9376. Min Act: -0.0000

Data Index: 134127 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9805. Min Act: -0.0000

Data Index: 271729 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9298. Min Act: -0.0000

Data Index: 960755 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9522. Min Act: -0.0000

Data Index: 864647 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1218991 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9354. Min Act: -0.0000

Data Index: 108137 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9041. Min Act: -0.0000

Data Index: 910799 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9214. Min Act: -0.0000

Data Index: 462725 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.1808. Min Range: -1.1808

Max Act: 0.9034. Min Act: -0.0000

Data Index: 694893 (C4 (Web Text))

Max Activating Token Index: 113