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

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

Neuron 2584 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5472. Min Range: -3.5472

Max Act: 3.5472. Min Act: -0.0000

Data Index: 1519418 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.6882. Min Act: -0.0000

Data Index: 1519789 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1532760 (Python Code)

Max Activating Token Index: 781

Text #3

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.5897. Min Act: -0.0000

Data Index: 1517119 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.5728. Min Act: -0.0000

Data Index: 1340263 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.7235. Min Act: -0.0000

Data Index: 1427441 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.6337. Min Act: -0.0000

Data Index: 1482914 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.5708. Min Act: -0.0000

Data Index: 1579937 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.4150. Min Act: -0.0000

Data Index: 1655289 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.3941. Min Act: -0.0000

Data Index: 2217 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2326. Min Act: -0.0000

Data Index: 1547515 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.1911. Min Act: -0.0000

Data Index: 8474 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2432. Min Act: -0.0000

Data Index: 1587350 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1442381 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2544. Min Act: -0.0000

Data Index: 1424980 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2363. Min Act: -0.0000

Data Index: 1643082 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2316. Min Act: -0.0000

Data Index: 733386 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1536569 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.0562. Min Act: -0.0000

Data Index: 1564368 (Python Code)

Max Activating Token Index: 570

Text #19

Max Range: 3.5472. Min Range: -3.5472

Max Act: 2.0063. Min Act: -0.0000

Data Index: 1634456 (Python Code)

Max Activating Token Index: 978