Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 451 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0027. Min Act: -0.0003

Data Index: 911033 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1342558 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0027. Min Act: -0.0003

Data Index: 38710 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 253741 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 508227 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 153812 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 997844 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 58395 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0024. Min Act: -0.0003

Data Index: 23667 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0026. Min Act: -0.0003

Data Index: 1107797 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 308520 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 129713 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 331767 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0024. Min Act: -0.0003

Data Index: 776810 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 354939 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 284634 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 490722 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0025. Min Act: -0.0003

Data Index: 789730 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0023. Min Act: -0.0003

Data Index: 284532 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0027. Min Range: -0.0027

Max Act: 0.0024. Min Act: -0.0003

Data Index: 1168906 (C4 (Web Text))

Max Activating Token Index: 814