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

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

Neuron 1723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.7666. Min Act: -0.0000

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.8864. Min Act: -0.0000

Data Index: 358222 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.0102. Min Range: -3.0102

Max Act: 3.0102. Min Act: -0.0000

Data Index: 1083226 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.9984. Min Act: -0.0000

Data Index: 800001 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.7334. Min Act: -0.0000

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.7392. Min Act: -0.0000

Data Index: 1051047 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.6294. Min Act: -0.0000

Data Index: 815428 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1085375 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.5627. Min Act: -0.0000

Data Index: 247479 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.3974. Min Act: -0.0000

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.5099. Min Act: -0.0000

Data Index: 670093 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.5029. Min Act: -0.0000

Data Index: 624165 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.4917. Min Act: -0.0000

Data Index: 1153542 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.4722. Min Act: -0.0000

Data Index: 1125711 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.4866. Min Act: -0.0000

Data Index: 722398 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.3180. Min Act: -0.0000

Data Index: 559433 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.3901. Min Act: -0.0000

Data Index: 560693 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.3671. Min Act: -0.0000

Data Index: 989798 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.1770. Min Act: -0.0000

Data Index: 623081 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 3.0102. Min Range: -3.0102

Max Act: 2.4083. Min Act: -0.0000

Data Index: 868820 (C4 (Web Text))

Max Activating Token Index: 391