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

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

Neuron 1999 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0066. Min Act: -0.0006

Data Index: 130112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1098927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0063. Min Act: -0.0006

Data Index: 575773 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1179279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0056. Min Act: -0.0006

Data Index: 537199 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0055. Min Act: -0.0006

Data Index: 1005735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0054. Min Act: -0.0006

Data Index: 84122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1502538 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1115983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0006

Data Index: 695874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0006

Data Index: 780555 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1117233 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0006

Data Index: 326597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0005

Data Index: 294621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0006

Data Index: 18808 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0052. Min Act: -0.0005

Data Index: 453922 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0053. Min Act: -0.0006

Data Index: 326241 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1437493 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0051. Min Act: -0.0005

Data Index: 973371 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0050. Min Act: -0.0006

Data Index: 290669 (C4 (Web Text))

Max Activating Token Index: 1023