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

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

Neuron 2614 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: 1.0852. Min Range: -1.0852

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1149400 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0852. Min Act: -0.0000

Data Index: 861456 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0852. Min Range: -1.0852

Max Act: 1.0426. Min Act: -0.0000

Data Index: 879150 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1281197 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8814. Min Act: -0.0000

Data Index: 267799 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8482. Min Act: -0.0000

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8577. Min Act: -0.0000

Data Index: 16886 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1123711 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8080. Min Act: -0.0000

Data Index: 770432 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8509. Min Act: -0.0000

Data Index: 409864 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8489. Min Act: -0.0000

Data Index: 53794 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1283263 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8252. Min Act: -0.0000

Data Index: 567938 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7591. Min Act: -0.0000

Data Index: 698672 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1217855 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1339689 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1237568 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1293318 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7589. Min Act: -0.0000

Data Index: 857632 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.0852. Min Range: -1.0852

Max Act: 0.7219. Min Act: -0.0000

Data Index: 471047 (C4 (Web Text))

Max Activating Token Index: 177