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

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

Neuron 1730 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: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1273579 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0048. Min Act: -0.0006

Data Index: 959821 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0005

Data Index: 29673 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0006

Data Index: 217088 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0006

Data Index: 596542 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0005

Data Index: 391255 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 302474 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 361958 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 50510 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1208760 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 994659 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 593293 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 752590 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 909769 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0043. Min Act: -0.0005

Data Index: 29309 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1070508 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0005

Data Index: 1199339 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1092782 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0006

Data Index: 464891 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1101623 (C4 (Web Text))

Max Activating Token Index: 473