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

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

Neuron 2195 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0034. Min Range: -3.0034

Max Act: 3.0034. Min Act: -0.0000

Data Index: 1453886 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.8938. Min Act: -0.0000

Data Index: 1568278 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.6913. Min Act: -0.0000

Data Index: 1618184 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.8994. Min Act: -0.0000

Data Index: 1584480 (Python Code)

Max Activating Token Index: 666

Text #4

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.8115. Min Act: -0.0000

Data Index: 1503387 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.1136. Min Act: -0.0000

Data Index: 1614551 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.4112. Min Act: -0.0000

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.1209. Min Act: -0.0000

Data Index: 1466636 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 3.0034. Min Range: -3.0034

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1561592 (Python Code)

Max Activating Token Index: 279

Text #9

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.8410. Min Act: -0.0000

Data Index: 55753 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.9234. Min Act: -0.0000

Data Index: 1459792 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1531494 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.8109. Min Act: -0.0000

Data Index: 1386305 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.6834. Min Act: -0.0000

Data Index: 1578616 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1584110 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1550681 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1446858 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1640508 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.6036. Min Act: -0.0000

Data Index: 291717 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 3.0034. Min Range: -3.0034

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1590990 (Python Code)

Max Activating Token Index: 152