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

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

Neuron 5998 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: 1.1860. Min Range: -1.1860

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1477536 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 1.1860. Min Range: -1.1860

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1612388 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 1.1860. Min Range: -1.1860

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1474030 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1461311 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1396093 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1400039 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1437358 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1405216 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1526330 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1579665 (Python Code)

Max Activating Token Index: 377

Text #10

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1481498 (Python Code)

Max Activating Token Index: 404

Text #11

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1583397 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1370782 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1534264 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1578268 (Python Code)

Max Activating Token Index: 667

Text #15

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1515375 (Python Code)

Max Activating Token Index: 152

Text #16

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1626004 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1579207 (Python Code)

Max Activating Token Index: 816

Text #18

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1366649 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 1.1860. Min Range: -1.1860

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1425861 (Python Code)

Max Activating Token Index: 610