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

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

Neuron 805 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: 5.0003. Min Range: -5.0003

Max Act: 4.7606. Min Act: -0.0000

Data Index: 426898 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.9870. Min Act: -0.0000

Data Index: 432015 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 5.0003. Min Range: -5.0003

Max Act: 5.0003. Min Act: -0.0000

Data Index: 1341757 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.3974. Min Act: -0.0000

Data Index: 676833 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.5742. Min Act: -0.0000

Data Index: 211949 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.2790. Min Act: -0.0000

Data Index: 279868 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.0558. Min Act: -0.0000

Data Index: 949006 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.0760. Min Act: -0.0000

Data Index: 614213 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 5.0003. Min Range: -5.0003

Max Act: 4.0826. Min Act: -0.0000

Data Index: 215492 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.9731. Min Act: -0.0000

Data Index: 744987 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.9240. Min Act: -0.0000

Data Index: 632440 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.5614. Min Act: -0.0000

Data Index: 390533 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.6514. Min Act: -0.0000

Data Index: 397845 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.5070. Min Act: -0.0000

Data Index: 1031347 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.4970. Min Act: -0.0000

Data Index: 1352068 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.9591. Min Act: -0.0000

Data Index: 727715 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.2225. Min Act: -0.0000

Data Index: 165599 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.6870. Min Act: -0.0000

Data Index: 183271 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.3550. Min Act: -0.0000

Data Index: 255682 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 5.0003. Min Range: -5.0003

Max Act: 3.1860. Min Act: -0.0000

Data Index: 1092897 (C4 (Web Text))

Max Activating Token Index: 458