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

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

Neuron 5311 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: 1.2689. Min Range: -1.2689

Max Act: 1.2689. Min Act: -0.0000

Data Index: 99121 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1144842 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1446712 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1193525 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0543. Min Act: -0.0000

Data Index: 430523 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0421. Min Act: -0.0000

Data Index: 5506 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9685. Min Act: -0.0000

Data Index: 1501629 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1481456 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1606752 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1529130 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8243. Min Act: -0.0000

Data Index: 972560 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1574403 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1554521 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7901. Min Act: 0.0000

Data Index: 1407088 (Python Code)

Max Activating Token Index: 165

Text #14

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8125. Min Act: 0.0000

Data Index: 340884 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8470. Min Act: 0.0000

Data Index: 1589091 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7927. Min Act: -0.0000

Data Index: 200763 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1591519 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7312. Min Act: -0.0000

Data Index: 204258 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1518576 (Python Code)

Max Activating Token Index: 747