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

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

Neuron 434 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: 0.0118. Min Range: -0.0118

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1118829 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1403887 (Python Code)

Max Activating Token Index: 918

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1450616 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1483828 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1647170 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1602010 (Python Code)

Max Activating Token Index: 407

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1464938 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1382123 (Python Code)

Max Activating Token Index: 878

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1440542 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1424708 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1365216 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1623886 (Python Code)

Max Activating Token Index: 849

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1487985 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1535887 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1516941 (Python Code)

Max Activating Token Index: 696

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1441779 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1500503 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1275076 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1403081 (Python Code)

Max Activating Token Index: 680

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1456136 (Python Code)

Max Activating Token Index: 521