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

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

Neuron 1573 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.6780. Min Act: -0.0000

Data Index: 1307135 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.4801. Min Act: -0.0000

Data Index: 1029703 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1049. Min Act: -0.0000

Data Index: 115112 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.2583. Min Act: -0.0000

Data Index: 1073360 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1574. Min Act: -0.0000

Data Index: 580405 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 2.6780. Min Range: -2.6780

Max Act: 2.1068. Min Act: -0.0000

Data Index: 223040 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.6980. Min Act: -0.0000

Data Index: 54012 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5537. Min Act: -0.0000

Data Index: 774291 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5702. Min Act: -0.0000

Data Index: 260755 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.5102. Min Act: -0.0000

Data Index: 631288 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3396. Min Act: -0.0000

Data Index: 401348 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3459. Min Act: -0.0000

Data Index: 293410 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3653. Min Act: -0.0000

Data Index: 975227 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.2916. Min Act: -0.0000

Data Index: 605925 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3595. Min Act: -0.0000

Data Index: 574344 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.2504. Min Act: -0.0000

Data Index: 126721 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.2713. Min Act: -0.0000

Data Index: 15313 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.2818. Min Act: -0.0000

Data Index: 111568 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.3234. Min Act: -0.0000

Data Index: 143485 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 2.6780. Min Range: -2.6780

Max Act: 1.0730. Min Act: -0.0000

Data Index: 676511 (C4 (Web Text))

Max Activating Token Index: 662