Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 253 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0002

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0003

Data Index: 459138 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1192319 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0079. Min Act: -0.0002

Data Index: 850799 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0080. Min Act: -0.0003

Data Index: 990741 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0003

Data Index: 666316 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0003

Data Index: 994136 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0003

Data Index: 605575 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0077. Min Act: -0.0002

Data Index: 830829 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0077. Min Act: -0.0003

Data Index: 938605 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0002

Data Index: 648164 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0072. Min Act: -0.0003

Data Index: 890967 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0084. Min Act: -0.0003

Data Index: 9970 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1251397 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0003

Data Index: 895307 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0076. Min Act: -0.0003

Data Index: 18537 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0071. Min Act: -0.0003

Data Index: 705587 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1277290 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1032206 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1236700 (C4 (Web Text))

Max Activating Token Index: 8