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

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

Neuron 4616 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1371387 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1425261 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1528575 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1587576 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1540578 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1399004 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2408. Min Act: -0.0000

Data Index: 772315 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1110000 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1174346 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1547020 (Python Code)

Max Activating Token Index: 164

Text #10

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2172. Min Act: -0.0000

Data Index: 720356 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1435480 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1634465 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1607915 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1204889 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1563442 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1479952 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1410865 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.1877. Min Act: -0.0000

Data Index: 965616 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 862