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

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

Neuron 3023 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: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0002

Data Index: 931406 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0973. Min Act: -0.0002

Data Index: 943762 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1310487 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0896. Min Act: -0.0002

Data Index: 608203 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0888. Min Act: -0.0002

Data Index: 951754 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1167671 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0875. Min Act: -0.0002

Data Index: 826241 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1218346 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1609810 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0833. Min Act: -0.0002

Data Index: 782194 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0817. Min Act: -0.0002

Data Index: 401752 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0796. Min Act: -0.0002

Data Index: 500716 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0778. Min Act: -0.0002

Data Index: 586804 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0777. Min Act: -0.0002

Data Index: 796046 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0773. Min Act: -0.0002

Data Index: 104081 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0773. Min Act: -0.0002

Data Index: 394785 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1357378 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0755. Min Act: -0.0002

Data Index: 120598 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0751. Min Act: -0.0002

Data Index: 730327 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0737. Min Act: -0.0002

Data Index: 369344 (C4 (Web Text))

Max Activating Token Index: 11