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

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

Neuron 2029 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: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0006

Data Index: 993214 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0006

Data Index: 815480 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0006

Data Index: 393245 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0102. Min Act: -0.0006

Data Index: 392646 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1140504 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 22579 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1204243 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 586992 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0006

Data Index: 290935 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0096. Min Act: -0.0006

Data Index: 286973 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0098. Min Act: -0.0006

Data Index: 986318 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1114288 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 635308 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0094. Min Act: -0.0006

Data Index: 71790 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1097797 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0095. Min Act: -0.0006

Data Index: 249358 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0099. Min Act: -0.0006

Data Index: 963572 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1169006 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0094. Min Act: -0.0006

Data Index: 27904 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1335123 (C4 (Web Text))

Max Activating Token Index: 587