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

Dataset: The Pile

Neuron 368 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.8115. Min Act: -0.0000

Data Index: 456155 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.8008. Min Act: -0.0000

Data Index: 741665 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.7737. Min Act: -0.0000

Data Index: 263848 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1219066 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.6548. Min Act: -0.0000

Data Index: 227011 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.6588. Min Act: -0.0000

Data Index: 253694 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.6326. Min Act: -0.0000

Data Index: 265179 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1849920 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1871711 (The Pile)

Max Activating Token Index: 868

Text #9

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5621. Min Act: 0.0000

Data Index: 80723 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1630262 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1106254 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5783. Min Act: -0.0000

Data Index: 870954 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1604944 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1600674 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1501985 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5327. Min Act: -0.0000

Data Index: 506733 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1273201 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1025413 (The Pile)

Max Activating Token Index: 219

Text #19

Max Range: 0.8115. Min Range: -0.8115

Max Act: 0.5194. Min Act: -0.0000

Data Index: 494235 (The Pile)

Max Activating Token Index: 152