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

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

Neuron 2308 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 371559 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 743878 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 1085326 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 826002 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 1168620 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3702. Min Act: -0.0002

Data Index: 482594 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3596. Min Act: -0.0002

Data Index: 984763 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3165. Min Act: -0.0002

Data Index: 885096 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3204. Min Act: -0.0003

Data Index: 55432 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3161. Min Act: -0.0002

Data Index: 2165 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.3077. Min Act: -0.0002

Data Index: 597134 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.2787. Min Act: -0.0002

Data Index: 852327 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.2471. Min Act: -0.0002

Data Index: 467857 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.2215. Min Act: -0.0002

Data Index: 672211 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1880. Min Act: -0.0002

Data Index: 488445 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1909. Min Act: -0.0002

Data Index: 47178 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1919. Min Act: -0.0002

Data Index: 1090904 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1904. Min Act: -0.0003

Data Index: 595863 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1621. Min Act: -0.0002

Data Index: 1162297 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.3702. Min Range: -1.3702

Max Act: 1.1587. Min Act: -0.0002

Data Index: 783223 (C4 (Web Text))

Max Activating Token Index: 791