Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4072 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0003

Data Index: 33129 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0003

Data Index: 288691 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 948811 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1310269 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0003

Data Index: 794047 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0003

Data Index: 458798 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1226602 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0053. Min Act: -0.0003

Data Index: 37201 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0003

Data Index: 155953 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1044182 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0003

Data Index: 211631 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 588573 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 208758 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1141342 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0002

Data Index: 252316 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 339694 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0051. Min Act: -0.0003

Data Index: 392145 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 350133 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0050. Min Act: -0.0003

Data Index: 746062 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0049. Min Act: -0.0003

Data Index: 41941 (C4 (Web Text))

Max Activating Token Index: 107