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

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

Neuron 1251 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8587. Min Act: -0.0000

Data Index: 1644441 (Python Code)

Max Activating Token Index: 447

Text #1

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1236352 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7676. Min Act: -0.0000

Data Index: 1490857 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.8580. Min Act: -0.0000

Data Index: 513565 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1265536 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5668. Min Act: -0.0000

Data Index: 89041 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1085593 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6226. Min Act: -0.0000

Data Index: 798444 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.4967. Min Act: -0.0000

Data Index: 738825 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5136. Min Act: -0.0000

Data Index: 1202143 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1537299 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6671. Min Act: -0.0000

Data Index: 319632 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6615. Min Act: -0.0000

Data Index: 535381 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6540. Min Act: -0.0000

Data Index: 728534 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5028. Min Act: -0.0000

Data Index: 923665 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.6006. Min Act: -0.0000

Data Index: 838279 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1109367 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5900. Min Act: -0.0000

Data Index: 108495 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1492262 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 1.8587. Min Range: -1.8587

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1478310 (Python Code)

Max Activating Token Index: 376