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

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

Neuron 3748 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.7464. Min Act: -0.0000

Data Index: 195484 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.7750. Min Act: -0.0000

Data Index: 79076 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.7281. Min Act: -0.0000

Data Index: 455603 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.6667. Min Act: -0.0000

Data Index: 835516 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.6652. Min Act: -0.0000

Data Index: 772765 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1300115 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.6564. Min Act: -0.0000

Data Index: 593717 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.6006. Min Act: -0.0000

Data Index: 870547 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5531. Min Act: -0.0000

Data Index: 735730 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5932. Min Act: -0.0000

Data Index: 397804 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1315139 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5546. Min Act: -0.0000

Data Index: 687054 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1328181 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5125. Min Act: -0.0000

Data Index: 692863 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5328. Min Act: -0.0000

Data Index: 863206 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.5141. Min Act: -0.0000

Data Index: 474774 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1083165 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.3734. Min Act: -0.0000

Data Index: 568980 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1325258 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.7750. Min Range: -0.7750

Max Act: 0.3354. Min Act: -0.0000

Data Index: 862997 (C4 (Web Text))

Max Activating Token Index: 192