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

Dataset: The Pile

Neuron 3686 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.7225. Min Act: -0.0000

Data Index: 263170 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.7321. Min Act: -0.0000

Data Index: 922697 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6557. Min Act: -0.0000

Data Index: 729198 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6862. Min Act: -0.0000

Data Index: 23856 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1416763 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6365. Min Act: -0.0000

Data Index: 559978 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1384847 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1795482 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1115612 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1947594 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1868421 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5969. Min Act: -0.0000

Data Index: 681571 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1714366 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1143609 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5783. Min Act: -0.0000

Data Index: 785584 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5786. Min Act: -0.0000

Data Index: 949966 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1063467 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1917139 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1243605 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1239371 (The Pile)

Max Activating Token Index: 692