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

Dataset: The Pile

Neuron 1667 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1441552 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1789262 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5986. Min Act: -0.0000

Data Index: 694796 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5992. Min Act: -0.0000

Data Index: 1823007 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5874. Min Act: -0.0000

Data Index: 610410 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5703. Min Act: -0.0000

Data Index: 111305 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1001982 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1632014 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5950. Min Act: -0.0000

Data Index: 118079 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5295. Min Act: -0.0000

Data Index: 792587 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5293. Min Act: -0.0000

Data Index: 308181 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1799931 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1540028 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1619312 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5751. Min Act: -0.0000

Data Index: 206353 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5404. Min Act: -0.0000

Data Index: 236810 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5405. Min Act: -0.0000

Data Index: 410309 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1160018 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1494109 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5531. Min Act: -0.0000

Data Index: 128475 (The Pile)

Max Activating Token Index: 661