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

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

Neuron 1343 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0771. Min Act: -0.0003

Data Index: 1395304 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0741. Min Act: -0.0003

Data Index: 718869 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0732. Min Act: -0.0003

Data Index: 735423 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0725. Min Act: -0.0003

Data Index: 227760 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1342608 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0706. Min Act: -0.0003

Data Index: 45387 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0718. Min Act: -0.0004

Data Index: 628490 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0711. Min Act: -0.0003

Data Index: 757951 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0698. Min Act: -0.0003

Data Index: 84934 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0690. Min Act: -0.0004

Data Index: 268457 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1152701 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0678. Min Act: -0.0003

Data Index: 668125 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1273929 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1297514 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1636221 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0666. Min Act: -0.0002

Data Index: 871790 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0674. Min Act: -0.0003

Data Index: 129799 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0688. Min Act: -0.0002

Data Index: 634788 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0687. Min Act: -0.0002

Data Index: 773529 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0771. Min Range: -0.0771

Max Act: 0.0648. Min Act: -0.0003

Data Index: 762903 (C4 (Web Text))

Max Activating Token Index: 135