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

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

Neuron 1492 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0762. Min Act: -0.0002

Data Index: 12200 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0740. Min Act: -0.0002

Data Index: 938095 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0730. Min Act: -0.0002

Data Index: 214206 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0677. Min Act: -0.0002

Data Index: 4092 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0749. Min Act: -0.0002

Data Index: 859625 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1200906 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0662. Min Act: -0.0002

Data Index: 556447 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0691. Min Act: -0.0002

Data Index: 690213 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0683. Min Act: -0.0002

Data Index: 12278 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1348276 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0683. Min Act: -0.0002

Data Index: 598042 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0662. Min Act: -0.0002

Data Index: 251616 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0646. Min Act: -0.0002

Data Index: 711073 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0679. Min Act: -0.0002

Data Index: 464291 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1185366 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1222899 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0650. Min Act: -0.0002

Data Index: 299001 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0642. Min Act: -0.0002

Data Index: 707107 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1155362 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.0762. Min Range: -0.0762

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1281204 (C4 (Web Text))

Max Activating Token Index: 478