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

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

Neuron 883 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: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 130333 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1141152 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 973388 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1215182 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0006

Data Index: 364442 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 152339 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 21132 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0078. Min Act: -0.0006

Data Index: 769696 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 859825 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 581869 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1182248 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 367307 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1021565 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 958616 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 59626 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 854767 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 259512 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 501814 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1166761 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0073. Min Act: -0.0006

Data Index: 1191069 (C4 (Web Text))

Max Activating Token Index: 35