Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1914 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0006

Data Index: 504562 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0006

Data Index: 210038 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1538202 (Python Code)

Max Activating Token Index: 978

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0006

Data Index: 298697 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1068368 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 448677 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0006

Data Index: 641729 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1412980 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0082. Min Act: -0.0006

Data Index: 507807 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 845299 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1402344 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1650810 (Python Code)

Max Activating Token Index: 526

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0082. Min Act: -0.0005

Data Index: 1612475 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1296220 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 214192 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0084. Min Act: -0.0006

Data Index: 636641 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1655783 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0075. Min Act: -0.0006

Data Index: 663807 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0006

Data Index: 805568 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0006

Data Index: 346098 (C4 (Web Text))

Max Activating Token Index: 832