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

Dataset: The Pile

Neuron 4832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1865187 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3531. Min Act: -0.0000

Data Index: 540255 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3430. Min Act: -0.0000

Data Index: 204295 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3212. Min Act: -0.0000

Data Index: 373572 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3260. Min Act: -0.0000

Data Index: 235320 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3189. Min Act: -0.0000

Data Index: 178407 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1953266 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1038639 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1423931 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2965. Min Act: -0.0000

Data Index: 590392 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3053. Min Act: -0.0000

Data Index: 510199 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1013760 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1857715 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2893. Min Act: -0.0000

Data Index: 25456 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1704171 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1391655 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1016592 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1448936 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3103. Min Act: -0.0000

Data Index: 246720 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2923. Min Act: -0.0000

Data Index: 629625 (The Pile)

Max Activating Token Index: 702