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

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

Neuron 4057 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: 0.7884. Min Range: -0.7884

Max Act: 0.7884. Min Act: -0.0001

Data Index: 1568102 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1405647 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1426566 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7295. Min Act: -0.0001

Data Index: 1367226 (Python Code)

Max Activating Token Index: 236

Text #4

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6598. Min Act: -0.0001

Data Index: 1222984 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6564. Min Act: -0.0001

Data Index: 788129 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6622. Min Act: -0.0001

Data Index: 647604 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6718. Min Act: -0.0001

Data Index: 1579534 (Python Code)

Max Activating Token Index: 819

Text #8

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6526. Min Act: -0.0001

Data Index: 534581 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1457564 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6671. Min Act: -0.0001

Data Index: 415778 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1635724 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1461760 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.7483. Min Act: -0.0001

Data Index: 538762 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1298829 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6446. Min Act: -0.0001

Data Index: 902507 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5572. Min Act: -0.0001

Data Index: 1457854 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5795. Min Act: -0.0001

Data Index: 117967 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.5761. Min Act: -0.0001

Data Index: 1464903 (Python Code)

Max Activating Token Index: 100

Text #19

Max Range: 0.7884. Min Range: -0.7884

Max Act: 0.6281. Min Act: -0.0001

Data Index: 785440 (C4 (Web Text))

Max Activating Token Index: 584