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

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

Neuron 4331 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0000

Data Index: 638103 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0922. Min Act: -0.0000

Data Index: 508247 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0772. Min Act: -0.0000

Data Index: 160868 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1089136 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1127055 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0686. Min Act: -0.0000

Data Index: 678879 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0638. Min Act: -0.0000

Data Index: 733893 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0676. Min Act: -0.0000

Data Index: 585528 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0641. Min Act: -0.0000

Data Index: 64970 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0605. Min Act: -0.0000

Data Index: 419298 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0642. Min Act: -0.0000

Data Index: 529290 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0611. Min Act: -0.0000

Data Index: 681752 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0557. Min Act: -0.0000

Data Index: 422016 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0607. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0580. Min Act: -0.0000

Data Index: 334629 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0598. Min Act: -0.0000

Data Index: 743493 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0615. Min Act: -0.0000

Data Index: 523455 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0590. Min Act: -0.0000

Data Index: 229430 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0602. Min Act: -0.0000

Data Index: 317652 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1292029 (C4 (Web Text))

Max Activating Token Index: 505