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

Dataset: The Pile

Neuron 3584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4798. Min Act: -0.0000

Data Index: 940250 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4555. Min Act: -0.0000

Data Index: 481695 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1615043 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1070665 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4142. Min Act: -0.0000

Data Index: 273207 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1438263 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1291381 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3710. Min Act: -0.0000

Data Index: 541976 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1935555 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3560. Min Act: -0.0000

Data Index: 687964 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3449. Min Act: -0.0000

Data Index: 198072 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1592535 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1038709 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1007548 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1524321 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1648923 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1177265 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1482534 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1518276 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1923890 (The Pile)

Max Activating Token Index: 462