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

Dataset: The Pile

Neuron 2030 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: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1543201 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1758395 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1431594 (The Pile)

Max Activating Token Index: 708

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1886976 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1934259 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1233587 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1888003 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4787. Min Act: -0.0000

Data Index: 110558 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4632. Min Act: -0.0000

Data Index: 353218 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4515. Min Act: -0.0000

Data Index: 379429 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4697. Min Act: -0.0000

Data Index: 148531 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4795. Min Act: -0.0000

Data Index: 373285 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1126812 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3986. Min Act: -0.0000

Data Index: 186264 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3992. Min Act: -0.0000

Data Index: 31205 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1018813 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1113817 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4008. Min Act: -0.0000

Data Index: 911473 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4309. Min Act: -0.0000

Data Index: 612131 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3889. Min Act: -0.0000

Data Index: 224125 (The Pile)

Max Activating Token Index: 114