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

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

Neuron 6017 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: 1.1337. Min Range: -1.1337

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1384686 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.8588. Min Act: -0.0000

Data Index: 1479357 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7565. Min Act: -0.0000

Data Index: 987013 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1534619 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7483. Min Act: -0.0000

Data Index: 149097 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1357204 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7130. Min Act: -0.0000

Data Index: 177895 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1317460 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7374. Min Act: -0.0000

Data Index: 228047 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6786. Min Act: -0.0000

Data Index: 117544 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7534. Min Act: -0.0000

Data Index: 114600 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6940. Min Act: -0.0000

Data Index: 467114 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1620716 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1178359 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6728. Min Act: -0.0000

Data Index: 500973 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1398698 (Python Code)

Max Activating Token Index: 121

Text #16

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6648. Min Act: -0.0000

Data Index: 268650 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1350781 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6923. Min Act: -0.0000

Data Index: 473380 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.1337. Min Range: -1.1337

Max Act: 0.6437. Min Act: -0.0000

Data Index: 129714 (C4 (Web Text))

Max Activating Token Index: 526