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

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

Neuron 1882 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1123879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0005

Data Index: 1651492 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1563094 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1429099 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1543289 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1544251 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1612292 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 807821 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1024241 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 29779 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1418886 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0006

Data Index: 336142 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0006

Data Index: 976781 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 218217 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1505465 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 386313 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1352756 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1281887 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1303013 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0006

Data Index: 545224 (C4 (Web Text))

Max Activating Token Index: 386