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

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

Neuron 44 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1104399 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1438597 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0094. Min Act: -0.0004

Data Index: 552192 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1388083 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0090. Min Act: -0.0003

Data Index: 484271 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0100. Min Act: -0.0003

Data Index: 682073 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1211702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1302804 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1168251 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1003430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0074. Min Act: -0.0004

Data Index: 1015447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1633976 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0090. Min Act: -0.0003

Data Index: 151925 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1559282 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0087. Min Act: -0.0003

Data Index: 367692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0079. Min Act: -0.0003

Data Index: 310974 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0077. Min Act: -0.0003

Data Index: 441442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1249624 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0077. Min Act: -0.0003

Data Index: 677767 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1498694 (Python Code)

Max Activating Token Index: 1023