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

Dataset: The Pile

Neuron 3254 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: 0.5508. Min Range: -0.5508

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1944109 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1006102 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4660. Min Act: -0.0000

Data Index: 434093 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1185083 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1624474 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4519. Min Act: -0.0000

Data Index: 924296 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.5193. Min Act: -0.0000

Data Index: 854076 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1314756 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4216. Min Act: -0.0000

Data Index: 107580 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1568163 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4096. Min Act: -0.0000

Data Index: 499033 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1453259 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4148. Min Act: -0.0000

Data Index: 496425 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1743801 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3961. Min Act: -0.0000

Data Index: 803148 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.4255. Min Act: -0.0000

Data Index: 320508 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1132611 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3964. Min Act: -0.0000

Data Index: 313121 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3980. Min Act: -0.0000

Data Index: 907398 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.5508. Min Range: -0.5508

Max Act: 0.3851. Min Act: -0.0000

Data Index: 467609 (The Pile)

Max Activating Token Index: 1009