Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6317. Min Act: -0.0000

Data Index: 309571 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1307758 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6642. Min Act: -0.0000

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6002. Min Act: -0.0000

Data Index: 65040 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5725. Min Act: -0.0000

Data Index: 93182 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5368. Min Act: -0.0000

Data Index: 731919 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5563. Min Act: -0.0000

Data Index: 7998 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1093456 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1240589 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4473. Min Act: -0.0000

Data Index: 274044 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4422. Min Act: -0.0000

Data Index: 803839 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4506. Min Act: -0.0000

Data Index: 701905 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1238641 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4314. Min Act: -0.0000

Data Index: 972818 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3947. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4132. Min Act: -0.0000

Data Index: 377018 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1565729 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3896. Min Act: -0.0000

Data Index: 418509 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1146676 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3959. Min Act: -0.0000

Data Index: 837485 (C4 (Web Text))

Max Activating Token Index: 792