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

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

Neuron 6093 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7570. Min Act: -0.0000

Data Index: 1558053 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1635749 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1436265 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7792. Min Act: -0.0000

Data Index: 1389574 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1513168 (Python Code)

Max Activating Token Index: 78

Text #5

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1631798 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1428692 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1565432 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1525600 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1452622 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1411042 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6131. Min Act: -0.0000

Data Index: 1378723 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1597122 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.6168. Min Act: -0.0000

Data Index: 1414628 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1459175 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1401610 (Python Code)

Max Activating Token Index: 899

Text #16

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1389397 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4837. Min Act: -0.0000

Data Index: 1560893 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1507380 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 1.9381. Min Range: -1.9381

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1405725 (Python Code)

Max Activating Token Index: 67