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

Dataset: The Pile

Neuron 303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.3850. Min Range: -10.3850

Max Act: 10.2121. Min Act: -0.0000

Data Index: 1445972 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 10.3850. Min Range: -10.3850

Max Act: 10.3850. Min Act: -0.0000

Data Index: 315630 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 10.3850. Min Range: -10.3850

Max Act: 10.0864. Min Act: -0.0000

Data Index: 1754633 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7989. Min Act: -0.0000

Data Index: 674373 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.6663. Min Act: -0.0000

Data Index: 393841 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7838. Min Act: -0.0000

Data Index: 821151 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.9297. Min Act: -0.0000

Data Index: 646728 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7103. Min Act: -0.0000

Data Index: 591243 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 10.3850. Min Range: -10.3850

Max Act: 10.2329. Min Act: -0.0000

Data Index: 1253623 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.8216. Min Act: -0.0000

Data Index: 1503029 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7949. Min Act: -0.0000

Data Index: 1708206 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.6436. Min Act: -0.0000

Data Index: 1069359 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.4838. Min Act: -0.0000

Data Index: 407765 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7759. Min Act: -0.0000

Data Index: 1120841 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.7678. Min Act: -0.0000

Data Index: 1463192 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.9181. Min Act: -0.0000

Data Index: 705899 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.6099. Min Act: -0.0000

Data Index: 1782349 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.2168. Min Act: -0.0000

Data Index: 299274 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.9385. Min Act: -0.0000

Data Index: 1298911 (The Pile)

Max Activating Token Index: 222

Text #19

Max Range: 10.3850. Min Range: -10.3850

Max Act: 9.6437. Min Act: -0.0000

Data Index: 1170294 (The Pile)

Max Activating Token Index: 387