Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0975. Min Act: -0.0000

Data Index: 307388 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.9474. Min Act: -0.0000

Data Index: 167135 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.1134. Min Act: -0.0000

Data Index: 876937 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1149752 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0914. Min Act: -0.0000

Data Index: 386547 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0229. Min Act: -0.0000

Data Index: 691551 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0179. Min Act: -0.0000

Data Index: 800125 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0218. Min Act: -0.0000

Data Index: 160323 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1194486 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 1.1434. Min Range: -1.1434

Max Act: 1.0273. Min Act: -0.0000

Data Index: 803642 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.9353. Min Act: -0.0000

Data Index: 249455 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8299. Min Act: -0.0000

Data Index: 360646 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.9905. Min Act: -0.0000

Data Index: 875545 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8732. Min Act: -0.0000

Data Index: 885677 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1189639 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8510. Min Act: -0.0000

Data Index: 670247 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8717. Min Act: -0.0000

Data Index: 100752 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.6864. Min Act: -0.0000

Data Index: 521691 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8847. Min Act: -0.0000

Data Index: 620114 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.1434. Min Range: -1.1434

Max Act: 0.8485. Min Act: -0.0000

Data Index: 782411 (C4 (Web Text))

Max Activating Token Index: 211