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

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

Neuron 4684 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: 1.2815. Min Range: -1.2815

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1421080 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1566663 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1607407 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.2815. Min Act: -0.0000

Data Index: 41283 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1404227 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1565. Min Act: -0.0000

Data Index: 96512 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1273549 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1471. Min Act: -0.0000

Data Index: 1570434 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1013. Min Act: -0.0000

Data Index: 39993 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1384909 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0914. Min Act: -0.0000

Data Index: 430417 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0553. Min Act: -0.0000

Data Index: 497098 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1506224 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1187. Min Act: -0.0000

Data Index: 609057 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1568075 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.1462. Min Act: -0.0000

Data Index: 1501567 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1148016 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1641081 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.2815. Min Range: -1.2815

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1639717 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 1.2815. Min Range: -1.2815

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1649668 (Python Code)

Max Activating Token Index: 359