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

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

Neuron 2705 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: 0.6789. Min Range: -0.6789

Max Act: 0.6789. Min Act: -0.0000

Data Index: 424102 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6097. Min Act: -0.0000

Data Index: 964620 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1625008 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5972. Min Act: -0.0000

Data Index: 505582 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1120956 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.6392. Min Act: -0.0000

Data Index: 675834 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5760. Min Act: 0.0000

Data Index: 759302 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5366. Min Act: -0.0000

Data Index: 689913 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5434. Min Act: -0.0000

Data Index: 37054 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5568. Min Act: -0.0000

Data Index: 520677 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1162874 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5236. Min Act: -0.0000

Data Index: 824054 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5618. Min Act: -0.0000

Data Index: 927391 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1314433 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4991. Min Act: -0.0000

Data Index: 530079 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1114397 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4838. Min Act: -0.0000

Data Index: 535890 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.4765. Min Act: -0.0000

Data Index: 987864 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.6789. Min Range: -0.6789

Max Act: 0.5006. Min Act: -0.0000

Data Index: 714077 (C4 (Web Text))

Max Activating Token Index: 499