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

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

Neuron 1872 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0005

Data Index: 1496910 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0133. Min Act: -0.0006

Data Index: 850796 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1479915 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1418285 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0005

Data Index: 482903 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1538447 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 358192 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1563203 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1096369 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0005

Data Index: 112392 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1171365 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1165051 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1104580 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0006

Data Index: 540123 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0005

Data Index: 711724 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1370833 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0006

Data Index: 960589 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0119. Min Act: -0.0005

Data Index: 480988 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1645764 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0005

Data Index: 571036 (C4 (Web Text))

Max Activating Token Index: 10