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

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

Neuron 3706 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0002

Data Index: 910521 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1215473 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0002

Data Index: 470250 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0056. Min Act: -0.0002

Data Index: 798831 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 752846 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1294730 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 908141 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0002

Data Index: 684238 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0053. Min Act: -0.0002

Data Index: 168298 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 473269 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1015097 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1459301 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 353563 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 493714 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 462326 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 778870 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1024069 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0002

Data Index: 632751 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1148644 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 976895 (C4 (Web Text))

Max Activating Token Index: 997