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

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

Neuron 4630 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1229007 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.9162. Min Act: -0.0000

Data Index: 273295 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7123. Min Act: -0.0000

Data Index: 1073377 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1319519 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1087327 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7335. Min Act: -0.0000

Data Index: 64742 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1341797 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7505. Min Act: -0.0000

Data Index: 656526 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.7637. Min Act: -0.0000

Data Index: 703173 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.6538. Min Act: -0.0000

Data Index: 1024121 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.6265. Min Act: -0.0000

Data Index: 301911 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.6238. Min Act: -0.0000

Data Index: 685697 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.6136. Min Act: -0.0000

Data Index: 846876 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.5540. Min Act: -0.0000

Data Index: 811764 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.3788. Min Act: -0.0000

Data Index: 139541 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1013341 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.5129. Min Act: -0.0000

Data Index: 265283 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.5536. Min Act: -0.0000

Data Index: 262573 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.2295. Min Act: -0.0000

Data Index: 29204 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.9774. Min Range: -1.9774

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1270356 (C4 (Web Text))

Max Activating Token Index: 471