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

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

Neuron 2440 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.8281. Min Act: -0.0000

Data Index: 126982 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.7988. Min Act: -0.0000

Data Index: 915475 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.7550. Min Act: 0.0000

Data Index: 1038823 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1046908 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6509. Min Act: -0.0000

Data Index: 399130 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5869. Min Act: -0.0000

Data Index: 136605 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6215. Min Act: 0.0000

Data Index: 1119049 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.6006. Min Act: -0.0000

Data Index: 399867 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1293399 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5326. Min Act: 0.0000

Data Index: 1022350 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1215004 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1007198 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5673. Min Act: -0.0000

Data Index: 628423 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5593. Min Act: 0.0000

Data Index: 824850 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5673. Min Act: 0.0000

Data Index: 1286795 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5680. Min Act: -0.0000

Data Index: 850478 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1298566 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5496. Min Act: -0.0000

Data Index: 34079 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5428. Min Act: 0.0000

Data Index: 696785 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.8281. Min Range: -0.8281

Max Act: 0.5402. Min Act: 0.0000

Data Index: 563574 (C4 (Web Text))

Max Activating Token Index: 454