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

Dataset: The Pile

Neuron 68 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0389. Min Range: -1.0389

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1003409 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.9414. Min Act: -0.0000

Data Index: 602119 (The Pile)

Max Activating Token Index: 926

Text #2

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1195333 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1411567 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8762. Min Act: -0.0000

Data Index: 970282 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1463825 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1294002 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1792545 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7892. Min Act: -0.0000

Data Index: 694776 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1459887 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1869167 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.8086. Min Act: -0.0000

Data Index: 987948 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6986. Min Act: -0.0000

Data Index: 980639 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1790139 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7068. Min Act: -0.0000

Data Index: 512537 (The Pile)

Max Activating Token Index: 866

Text #15

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7142. Min Act: -0.0000

Data Index: 207620 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7716. Min Act: -0.0000

Data Index: 747716 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1168734 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.6301. Min Act: -0.0000

Data Index: 301878 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.0389. Min Range: -1.0389

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1470527 (The Pile)

Max Activating Token Index: 715