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

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

Neuron 589 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: 0.0105. Min Range: -0.0105

Max Act: 0.0105. Min Act: -0.0006

Data Index: 532086 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1496896 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1609851 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1514427 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1182311 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0092. Min Act: -0.0006

Data Index: 923769 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1145392 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1537389 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 357621 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0089. Min Act: -0.0006

Data Index: 19049 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1547372 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1495518 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 543398 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1409005 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1401856 (Python Code)

Max Activating Token Index: 372

Text #15

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0090. Min Act: -0.0005

Data Index: 965612 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0086. Min Act: -0.0006

Data Index: 19662 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0083. Min Act: -0.0005

Data Index: 223435 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0084. Min Act: -0.0006

Data Index: 461546 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0105. Min Range: -0.0105

Max Act: 0.0083. Min Act: -0.0006

Data Index: 990895 (C4 (Web Text))

Max Activating Token Index: 286