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

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

Neuron 1965 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: 0.6331. Min Range: -0.6331

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1553005 (Python Code)

Max Activating Token Index: 815

Text #1

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1069947 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1536467 (Python Code)

Max Activating Token Index: 674

Text #3

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1069882 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5524. Min Act: -0.0000

Data Index: 992172 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1344121 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5504. Min Act: -0.0000

Data Index: 31421 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1457950 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5299. Min Act: -0.0000

Data Index: 602401 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5330. Min Act: -0.0000

Data Index: 925903 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5166. Min Act: -0.0000

Data Index: 445469 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5410. Min Act: -0.0000

Data Index: 734352 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1122759 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1592686 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.4808. Min Act: -0.0000

Data Index: 632523 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.5350. Min Act: -0.0000

Data Index: 628436 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1072329 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.4922. Min Act: -0.0000

Data Index: 832450 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1010844 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.6331. Min Range: -0.6331

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1531897 (Python Code)

Max Activating Token Index: 720