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

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

Neuron 5648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9072. Min Range: -7.9072

Max Act: 7.9072. Min Act: -0.0001

Data Index: 1242255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.9072. Min Range: -7.9072

Max Act: 5.8142. Min Act: -0.0001

Data Index: 1531712 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 7.9072. Min Range: -7.9072

Max Act: 4.2902. Min Act: -0.0001

Data Index: 216325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 7.9072. Min Range: -7.9072

Max Act: 4.6601. Min Act: -0.0001

Data Index: 853866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.7640. Min Act: -0.0001

Data Index: 1443210 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 7.9072. Min Range: -7.9072

Max Act: 4.0245. Min Act: -0.0001

Data Index: 163433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.0800. Min Act: -0.0001

Data Index: 1645757 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.6503. Min Act: -0.0001

Data Index: 1584783 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.4387. Min Act: -0.0001

Data Index: 105401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.2475. Min Act: -0.0001

Data Index: 930332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 7.9072. Min Range: -7.9072

Max Act: 2.7403. Min Act: -0.0001

Data Index: 1515482 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.8031. Min Act: -0.0001

Data Index: 1291418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.4624. Min Act: -0.0001

Data Index: 1291343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.6331. Min Act: -0.0001

Data Index: 594643 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.4162. Min Act: -0.0001

Data Index: 1241902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.2119. Min Act: -0.0001

Data Index: 1240085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.3589. Min Act: -0.0001

Data Index: 111014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 7.9072. Min Range: -7.9072

Max Act: 2.6124. Min Act: -0.0001

Data Index: 579919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.4034. Min Act: -0.0001

Data Index: 1439151 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 7.9072. Min Range: -7.9072

Max Act: 3.1764. Min Act: -0.0001

Data Index: 1571674 (Python Code)

Max Activating Token Index: 1023