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

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

Neuron 3716 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3770. Min Act: -0.0001

Data Index: 85308 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3052. Min Act: -0.0001

Data Index: 567220 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3034. Min Act: -0.0001

Data Index: 1050214 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3036. Min Act: -0.0001

Data Index: 528455 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1051075 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.3122. Min Act: -0.0001

Data Index: 241313 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2811. Min Act: -0.0001

Data Index: 801551 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2950. Min Act: -0.0001

Data Index: 467360 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2654. Min Act: -0.0001

Data Index: 974330 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2778. Min Act: -0.0001

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2773. Min Act: -0.0001

Data Index: 751239 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2756. Min Act: -0.0001

Data Index: 260593 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2753. Min Act: -0.0001

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2743. Min Act: -0.0001

Data Index: 273861 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2845. Min Act: -0.0001

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2549. Min Act: -0.0001

Data Index: 324945 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2734. Min Act: -0.0001

Data Index: 166835 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.3770. Min Range: -0.3770

Max Act: 0.2713. Min Act: -0.0001

Data Index: 588970 (C4 (Web Text))

Max Activating Token Index: 444