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

Dataset: The Pile

Neuron 164 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: 0.7313. Min Range: -0.7313

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1568937 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.7069. Min Act: -0.0000

Data Index: 936676 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.7313. Min Act: -0.0000

Data Index: 406890 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6854. Min Act: -0.0000

Data Index: 951878 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6671. Min Act: -0.0000

Data Index: 943788 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1051854 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1153349 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6745. Min Act: -0.0000

Data Index: 169823 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1332994 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6068. Min Act: -0.0000

Data Index: 605768 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1000173 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1220887 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6301. Min Act: -0.0000

Data Index: 874463 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.5870. Min Act: -0.0000

Data Index: 860243 (The Pile)

Max Activating Token Index: 81

Text #14

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1791717 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1753126 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6276. Min Act: -0.0000

Data Index: 645048 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1639545 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1416607 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 0.7313. Min Range: -0.7313

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1051402 (The Pile)

Max Activating Token Index: 948