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

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

Neuron 850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0006

Data Index: 111695 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0006

Data Index: 817942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0107. Min Act: -0.0006

Data Index: 756968 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0006

Data Index: 209704 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0110. Min Act: -0.0006

Data Index: 330273 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1352756 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0104. Min Act: -0.0006

Data Index: 857503 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1222031 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0103. Min Act: -0.0006

Data Index: 876429 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1019429 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1151517 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1267909 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0100. Min Act: -0.0006

Data Index: 458675 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1222950 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0105. Min Act: -0.0006

Data Index: 930237 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0098. Min Act: -0.0006

Data Index: 888623 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0096. Min Act: -0.0006

Data Index: 32614 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1177174 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1261256 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0095. Min Act: -0.0006

Data Index: 208997 (C4 (Web Text))

Max Activating Token Index: 483