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

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

Neuron 255 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1430973 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1429211 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1569366 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1605530 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1567007 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1656753 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.3641. Min Act: -0.0000

Data Index: 1498452 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.5063. Min Act: -0.0000

Data Index: 1419256 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1628091 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1555376 (Python Code)

Max Activating Token Index: 896

Text #10

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1638059 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1652064 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1646733 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1455816 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1509908 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1371064 (Python Code)

Max Activating Token Index: 641

Text #16

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1577132 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1530014 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1506173 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 1.8518. Min Range: -1.8518

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1578283 (Python Code)

Max Activating Token Index: 938