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

Dataset: The Pile

Neuron 658 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: 0.6616. Min Range: -0.6616

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1879932 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6616. Min Act: -0.0000

Data Index: 50520 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1371492 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6252. Min Act: -0.0000

Data Index: 527108 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5967. Min Act: -0.0000

Data Index: 799376 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1858387 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6154. Min Act: -0.0000

Data Index: 855650 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6115. Min Act: -0.0000

Data Index: 442376 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1162979 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5645. Min Act: -0.0000

Data Index: 864139 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6459. Min Act: -0.0000

Data Index: 397759 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1424133 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1383710 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5816. Min Act: -0.0000

Data Index: 41615 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5974. Min Act: -0.0000

Data Index: 689005 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1453650 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1852277 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5773. Min Act: -0.0000

Data Index: 985151 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1675346 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.6616. Min Range: -0.6616

Max Act: 0.5775. Min Act: -0.0000

Data Index: 296477 (The Pile)

Max Activating Token Index: 65