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

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

Neuron 4849 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8845. Min Act: -0.0000

Data Index: 777536 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9583. Min Act: -0.0000

Data Index: 211941 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8950. Min Act: -0.0000

Data Index: 807609 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1156774 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7762. Min Act: -0.0001

Data Index: 371508 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7839. Min Act: -0.0001

Data Index: 231483 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7645. Min Act: -0.0001

Data Index: 657783 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7421. Min Act: -0.0001

Data Index: 31747 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7635. Min Act: -0.0000

Data Index: 801749 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7575. Min Act: -0.0001

Data Index: 1151641 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1080795 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.8117. Min Act: -0.0001

Data Index: 187639 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1288048 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6983. Min Act: -0.0001

Data Index: 1235611 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1181638 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7485. Min Act: -0.0000

Data Index: 707138 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7117. Min Act: -0.0000

Data Index: 541535 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7198. Min Act: -0.0001

Data Index: 983415 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.7295. Min Act: -0.0001

Data Index: 292922 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.9748. Min Range: -0.9748

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1026565 (C4 (Web Text))

Max Activating Token Index: 897