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

Dataset: The Pile

Neuron 1654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1381197 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1879047 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1502445 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2004. Min Act: -0.0000

Data Index: 832857 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1693960 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1995. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1951. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2035. Min Act: -0.0000

Data Index: 534841 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1317563 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1760038 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1842. Min Act: -0.0000

Data Index: 663741 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1450697 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2011. Min Act: -0.0000

Data Index: 624219 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1731. Min Act: -0.0000

Data Index: 22616 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1538868 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1862. Min Act: -0.0000

Data Index: 545152 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1624. Min Act: -0.0000

Data Index: 874231 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1850. Min Act: -0.0000

Data Index: 294749 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1519113 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1685. Min Act: -0.0000

Data Index: 132228 (The Pile)

Max Activating Token Index: 31