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

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

Neuron 3874 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1145094 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0102. Min Act: -0.0003

Data Index: 507002 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1147775 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0003

Data Index: 624578 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0003

Data Index: 898837 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0002

Data Index: 688353 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0003

Data Index: 62191 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0088. Min Act: -0.0003

Data Index: 965704 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0093. Min Act: -0.0003

Data Index: 73747 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0082. Min Act: -0.0003

Data Index: 630755 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0084. Min Act: -0.0003

Data Index: 158600 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1481453 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0079. Min Act: -0.0003

Data Index: 618043 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0079. Min Act: -0.0002

Data Index: 188414 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0087. Min Act: -0.0002

Data Index: 521159 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0084. Min Act: -0.0002

Data Index: 462520 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0080. Min Act: -0.0002

Data Index: 1371791 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0087. Min Act: -0.0003

Data Index: 207966 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1102289 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0080. Min Act: -0.0002

Data Index: 154076 (C4 (Web Text))

Max Activating Token Index: 55