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

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

Neuron 3474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.7507. Min Act: -0.0001

Data Index: 364571 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1220383 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.6884. Min Act: -0.0000

Data Index: 672807 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.6214. Min Act: -0.0000

Data Index: 895383 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5882. Min Act: -0.0001

Data Index: 222196 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.6173. Min Act: -0.0001

Data Index: 1010221 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4998. Min Act: -0.0000

Data Index: 675795 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5370. Min Act: -0.0001

Data Index: 740343 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5255. Min Act: -0.0001

Data Index: 620142 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1269716 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5444. Min Act: -0.0001

Data Index: 203557 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4059. Min Act: -0.0001

Data Index: 637580 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.5238. Min Act: -0.0000

Data Index: 446443 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4719. Min Act: -0.0001

Data Index: 470423 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4676. Min Act: -0.0001

Data Index: 365820 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.3720. Min Act: -0.0001

Data Index: 879499 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1076997 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4923. Min Act: -0.0000

Data Index: 749738 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4417. Min Act: -0.0001

Data Index: 449660 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.7507. Min Range: -1.7507

Max Act: 1.4458. Min Act: -0.0001

Data Index: 302445 (C4 (Web Text))

Max Activating Token Index: 120