Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3604 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1344922 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0110. Min Act: -0.0002

Data Index: 574404 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0106. Min Act: -0.0002

Data Index: 213650 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0115. Min Act: -0.0002

Data Index: 682032 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1292801 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0094. Min Act: -0.0002

Data Index: 919582 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0002

Data Index: 885477 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0090. Min Act: -0.0002

Data Index: 276319 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0092. Min Act: -0.0002

Data Index: 196050 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0105. Min Act: -0.0002

Data Index: 75872 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0087. Min Act: -0.0002

Data Index: 635662 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0092. Min Act: -0.0002

Data Index: 900075 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0095. Min Act: -0.0002

Data Index: 975831 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1506111 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1410265 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0095. Min Act: -0.0002

Data Index: 232826 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0081. Min Act: -0.0002

Data Index: 414023 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0096. Min Act: -0.0002

Data Index: 324942 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0088. Min Act: -0.0002

Data Index: 368539 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0096. Min Act: -0.0002

Data Index: 262969 (C4 (Web Text))

Max Activating Token Index: 735