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

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

Neuron 831 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1031. Min Range: -3.1031

Max Act: 3.1031. Min Act: -0.0000

Data Index: 1306748 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1395846 (Python Code)

Max Activating Token Index: 746

Text #2

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3512. Min Act: -0.0000

Data Index: 1412779 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.3147. Min Act: -0.0000

Data Index: 1208672 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.0767. Min Act: -0.0000

Data Index: 1493214 (Python Code)

Max Activating Token Index: 554

Text #5

Max Range: 3.1031. Min Range: -3.1031

Max Act: 2.0743. Min Act: -0.0000

Data Index: 1224625 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.8628. Min Act: -0.0000

Data Index: 1401267 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.9753. Min Act: -0.0000

Data Index: 1491116 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1480833 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.6569. Min Act: -0.0000

Data Index: 869489 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.8155. Min Act: -0.0000

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.8282. Min Act: -0.0000

Data Index: 1236265 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1208551 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1401247 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.6125. Min Act: -0.0000

Data Index: 1381811 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1557728 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.5121. Min Act: -0.0000

Data Index: 75226 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.6189. Min Act: -0.0000

Data Index: 1553924 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.5223. Min Act: -0.0000

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 3.1031. Min Range: -3.1031

Max Act: 1.5985. Min Act: -0.0000

Data Index: 820039 (C4 (Web Text))

Max Activating Token Index: 983