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

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

Neuron 222 in Layer 0

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: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0001

Data Index: 840209 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0887. Min Act: -0.0001

Data Index: 847866 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0896. Min Act: -0.0001

Data Index: 149182 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0850. Min Act: -0.0001

Data Index: 160555 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0828. Min Act: -0.0002

Data Index: 980652 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1314748 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0812. Min Act: -0.0001

Data Index: 322947 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1247246 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0740. Min Act: -0.0001

Data Index: 589776 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0742. Min Act: -0.0001

Data Index: 159133 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0714. Min Act: -0.0001

Data Index: 769560 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0716. Min Act: -0.0001

Data Index: 24984 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0715. Min Act: -0.0001

Data Index: 686500 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0709. Min Act: -0.0001

Data Index: 606127 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0722. Min Act: -0.0001

Data Index: 661107 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0697. Min Act: -0.0001

Data Index: 8144 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0718. Min Act: -0.0002

Data Index: 89272 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1105797 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1228592 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1278874 (C4 (Web Text))

Max Activating Token Index: 19