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

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

Neuron 1025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.1014. Min Act: -0.0000

Data Index: 765897 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.1014. Min Range: -2.1014

Max Act: 2.0544. Min Act: -0.0000

Data Index: 753121 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9979. Min Act: -0.0000

Data Index: 588843 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.9046. Min Act: -0.0000

Data Index: 1136395 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.7548. Min Act: -0.0001

Data Index: 1459839 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.7542. Min Act: -0.0000

Data Index: 751389 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6492. Min Act: -0.0000

Data Index: 512797 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1167291 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1031860 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.7101. Min Act: -0.0000

Data Index: 108646 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6666. Min Act: -0.0001

Data Index: 962084 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6508. Min Act: -0.0000

Data Index: 266299 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1215669 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1300854 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1252442 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.5747. Min Act: -0.0000

Data Index: 702708 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.5810. Min Act: -0.0000

Data Index: 178263 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.5737. Min Act: -0.0001

Data Index: 778130 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.6599. Min Act: -0.0000

Data Index: 101857 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 2.1014. Min Range: -2.1014

Max Act: 1.5958. Min Act: -0.0001

Data Index: 1636610 (Python Code)

Max Activating Token Index: 558