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

Dataset: The Pile

Neuron 3632 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: 1.0481. Min Range: -1.0481

Max Act: 1.0481. Min Act: -0.0000

Data Index: 558898 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8619. Min Act: -0.0000

Data Index: 389807 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1550431 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1768355 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6619. Min Act: -0.0000

Data Index: 46873 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1526637 (The Pile)

Max Activating Token Index: 760

Text #6

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1655317 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1715261 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1381622 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6170. Min Act: -0.0000

Data Index: 624372 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6284. Min Act: 0.0000

Data Index: 271427 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.5935. Min Act: -0.0000

Data Index: 359881 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6887. Min Act: -0.0000

Data Index: 857357 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1423252 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6404. Min Act: 0.0000

Data Index: 573115 (The Pile)

Max Activating Token Index: 277

Text #15

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1058458 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6009. Min Act: -0.0000

Data Index: 920273 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.5790. Min Act: -0.0000

Data Index: 658032 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1607128 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1711286 (The Pile)

Max Activating Token Index: 339