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

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

Neuron 1350 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: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1565887 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1462148 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 886831 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1429972 (Python Code)

Max Activating Token Index: 485

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1653397 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1578467 (Python Code)

Max Activating Token Index: 713

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0006

Data Index: 920786 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1628048 (Python Code)

Max Activating Token Index: 507

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 628544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1383553 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1444334 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1650421 (Python Code)

Max Activating Token Index: 742

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1604157 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1594159 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1395493 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0005

Data Index: 1584312 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1621251 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0006

Data Index: 999227 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 232043 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1414423 (Python Code)

Max Activating Token Index: 626