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

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

Neuron 5646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1118084 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2747. Min Act: -0.0000

Data Index: 414811 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1281507 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1262299 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1348206 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.1234. Min Act: -0.0000

Data Index: 350846 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0660. Min Act: -0.0000

Data Index: 650541 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9617. Min Act: -0.0000

Data Index: 199223 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.3628. Min Range: -1.3628

Max Act: 1.0122. Min Act: -0.0000

Data Index: 327455 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9989. Min Act: -0.0000

Data Index: 236598 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9470. Min Act: -0.0000

Data Index: 191608 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9622. Min Act: -0.0000

Data Index: 182748 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1137833 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1215441 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9821. Min Act: -0.0000

Data Index: 198554 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9077. Min Act: -0.0000

Data Index: 52101 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9255. Min Act: -0.0000

Data Index: 680966 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.9088. Min Act: 0.0000

Data Index: 555044 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.8897. Min Act: -0.0000

Data Index: 103372 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.3628. Min Range: -1.3628

Max Act: 0.8498. Min Act: -0.0000

Data Index: 349706 (C4 (Web Text))

Max Activating Token Index: 474