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

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

Neuron 506 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: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1485196 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0088. Min Act: -0.0006

Data Index: 455778 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1467601 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1084579 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0006

Data Index: 137231 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1575855 (Python Code)

Max Activating Token Index: 947

Text #6

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1288425 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0006

Data Index: 155424 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0006

Data Index: 253114 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1467709 (Python Code)

Max Activating Token Index: 945

Text #10

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0005

Data Index: 259860 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1599510 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1621688 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0006

Data Index: 240446 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1380760 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1468185 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0081. Min Act: -0.0006

Data Index: 325960 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1407752 (Python Code)

Max Activating Token Index: 497

Text #18

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0006

Data Index: 375673 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0005

Data Index: 1413149 (Python Code)

Max Activating Token Index: 28