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

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

Neuron 1692 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: 0.0089. Min Range: -0.0089

Max Act: 0.0089. Min Act: -0.0006

Data Index: 133024 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1203707 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0079. Min Act: -0.0006

Data Index: 294648 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0075. Min Act: -0.0006

Data Index: 24746 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0076. Min Act: -0.0006

Data Index: 239920 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0074. Min Act: -0.0006

Data Index: 785366 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0070. Min Act: -0.0006

Data Index: 544817 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0068. Min Act: -0.0006

Data Index: 630829 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0070. Min Act: -0.0006

Data Index: 309440 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0006

Data Index: 268851 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0069. Min Act: -0.0006

Data Index: 185432 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1234958 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0006

Data Index: 250599 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1205195 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1099044 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0066. Min Act: -0.0006

Data Index: 604733 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1023281 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0006

Data Index: 433340 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1138011 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0089. Min Range: -0.0089

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1119279 (C4 (Web Text))

Max Activating Token Index: 844