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

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

Neuron 1204 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: 0.6770. Min Range: -0.6770

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1493596 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1475267 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6443. Min Act: -0.0000

Data Index: 728553 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1551622 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6401. Min Act: -0.0000

Data Index: 15894 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6380. Min Act: 0.0000

Data Index: 1580522 (Python Code)

Max Activating Token Index: 630

Text #6

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6343. Min Act: -0.0000

Data Index: 219463 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1521361 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6048. Min Act: -0.0000

Data Index: 833356 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5722. Min Act: -0.0000

Data Index: 196849 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1200162 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5892. Min Act: 0.0000

Data Index: 1648499 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1322630 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6021. Min Act: 0.0000

Data Index: 1459196 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5770. Min Act: 0.0000

Data Index: 938643 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5771. Min Act: -0.0000

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1394294 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1443834 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5602. Min Act: -0.0000

Data Index: 737023 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5427. Min Act: -0.0000

Data Index: 415863 (C4 (Web Text))

Max Activating Token Index: 86