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

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

Neuron 2859 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4804. Min Range: -3.4804

Max Act: 3.4804. Min Act: -0.0000

Data Index: 305402 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.4804. Min Range: -3.4804

Max Act: 3.1766. Min Act: -0.0000

Data Index: 1045105 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.9607. Min Act: -0.0000

Data Index: 1124729 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.9482. Min Act: -0.0000

Data Index: 910940 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1327792 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.8071. Min Act: -0.0000

Data Index: 21293 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.8127. Min Act: -0.0000

Data Index: 66955 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.8883. Min Act: -0.0000

Data Index: 168189 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.8215. Min Act: -0.0000

Data Index: 378102 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.6739. Min Act: -0.0000

Data Index: 375353 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.6665. Min Act: -0.0000

Data Index: 1166690 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.6598. Min Act: -0.0000

Data Index: 1008842 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.5140. Min Act: -0.0000

Data Index: 316186 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.6511. Min Act: -0.0000

Data Index: 288480 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.3921. Min Act: -0.0000

Data Index: 13404 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.6040. Min Act: -0.0000

Data Index: 936993 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.5993. Min Act: -0.0000

Data Index: 329873 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.5942. Min Act: -0.0000

Data Index: 78007 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.5817. Min Act: -0.0000

Data Index: 348698 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.4804. Min Range: -3.4804

Max Act: 2.5873. Min Act: -0.0000

Data Index: 538342 (C4 (Web Text))

Max Activating Token Index: 953