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

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

Neuron 2153 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: 0.0151. Min Range: -0.0151

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1287340 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0125. Min Act: -0.0003

Data Index: 930269 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0120. Min Act: -0.0003

Data Index: 673183 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1276957 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0113. Min Act: -0.0002

Data Index: 269834 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0108. Min Act: -0.0002

Data Index: 532895 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0115. Min Act: -0.0003

Data Index: 202094 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0109. Min Act: -0.0003

Data Index: 909350 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0109. Min Act: -0.0002

Data Index: 981139 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0102. Min Act: -0.0003

Data Index: 505342 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0104. Min Act: -0.0002

Data Index: 293896 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0103. Min Act: -0.0003

Data Index: 65150 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0105. Min Act: -0.0002

Data Index: 649714 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0101. Min Act: -0.0002

Data Index: 992030 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1630244 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0100. Min Act: -0.0002

Data Index: 9783 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0102. Min Act: -0.0003

Data Index: 523306 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0102. Min Act: -0.0003

Data Index: 932828 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0102. Min Act: -0.0003

Data Index: 370744 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0151. Min Range: -0.0151

Max Act: 0.0101. Min Act: -0.0003

Data Index: 355665 (C4 (Web Text))

Max Activating Token Index: 16