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

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

Neuron 1859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.3468. Min Range: -4.3468

Max Act: 4.1795. Min Act: -0.0000

Data Index: 395708 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 4.3468. Min Range: -4.3468

Max Act: 4.3468. Min Act: -0.0000

Data Index: 908663 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 4.3468. Min Range: -4.3468

Max Act: 4.0003. Min Act: -0.0000

Data Index: 1100994 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.6356. Min Act: -0.0000

Data Index: 1630696 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.6793. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.7850. Min Act: -0.0000

Data Index: 1543862 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.8599. Min Act: -0.0000

Data Index: 1362584 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.5948. Min Act: -0.0000

Data Index: 1373187 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.4239. Min Act: -0.0000

Data Index: 1557416 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.5712. Min Act: -0.0000

Data Index: 887455 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.0822. Min Act: -0.0000

Data Index: 1589758 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.4880. Min Act: -0.0000

Data Index: 859220 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.6432. Min Act: -0.0000

Data Index: 600578 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.3063. Min Act: -0.0000

Data Index: 1342868 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.4302. Min Act: -0.0000

Data Index: 826950 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.1974. Min Act: -0.0000

Data Index: 1145934 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1632448 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.3549. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.3282. Min Act: -0.0000

Data Index: 100123 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 4.3468. Min Range: -4.3468

Max Act: 3.4712. Min Act: -0.0000

Data Index: 1572206 (Python Code)

Max Activating Token Index: 984