Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1413 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1355211 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0111. Min Act: -0.0006

Data Index: 945813 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1573517 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1348669 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1229989 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0106. Min Act: -0.0006

Data Index: 618443 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1132072 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0107. Min Act: -0.0006

Data Index: 779073 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0097. Min Act: -0.0006

Data Index: 608670 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0104. Min Act: -0.0006

Data Index: 257925 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1254542 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0103. Min Act: -0.0006

Data Index: 182497 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0006

Data Index: 377082 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0105. Min Act: -0.0006

Data Index: 47037 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0006

Data Index: 528636 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0101. Min Act: -0.0005

Data Index: 288910 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0108. Min Act: -0.0006

Data Index: 373810 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0102. Min Act: -0.0006

Data Index: 60152 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0099. Min Act: -0.0006

Data Index: 904822 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0113. Min Range: -0.0113

Max Act: 0.0098. Min Act: -0.0006

Data Index: 406099 (C4 (Web Text))

Max Activating Token Index: 959