Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3483 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.9501. Min Act: -0.0000

Data Index: 88178 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7640. Min Act: -0.0000

Data Index: 567188 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7842. Min Act: -0.0000

Data Index: 502289 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6881. Min Act: -0.0000

Data Index: 41576 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1652876 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6956. Min Act: -0.0000

Data Index: 232197 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7409. Min Act: -0.0000

Data Index: 446983 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1108761 (The Pile)

Max Activating Token Index: 63

Text #8

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1124436 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1577033 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7242. Min Act: -0.0000

Data Index: 693479 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1885983 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.7161. Min Act: -0.0000

Data Index: 257714 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6975. Min Act: -0.0000

Data Index: 905752 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6408. Min Act: -0.0000

Data Index: 530402 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6143. Min Act: -0.0000

Data Index: 204778 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.5907. Min Act: -0.0000

Data Index: 92382 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1299729 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1932322 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.9501. Min Range: -0.9501

Max Act: 0.6321. Min Act: -0.0000

Data Index: 750706 (The Pile)

Max Activating Token Index: 478