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

Dataset: The Pile

Neuron 2367 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: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0000

Data Index: 367928 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1210587 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0792. Min Act: -0.0000

Data Index: 291412 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0761. Min Act: -0.0000

Data Index: 23857 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0747. Min Act: -0.0000

Data Index: 308398 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1155692 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0710. Min Act: -0.0000

Data Index: 192115 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0681. Min Act: -0.0000

Data Index: 370453 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0673. Min Act: -0.0000

Data Index: 869234 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0669. Min Act: -0.0000

Data Index: 421096 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1480906 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1166400 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1783425 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1944433 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1574437 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0677. Min Act: -0.0000

Data Index: 859588 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0630. Min Act: -0.0000

Data Index: 956118 (The Pile)

Max Activating Token Index: 699

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1594556 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1666668 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0666. Min Act: -0.0000

Data Index: 372011 (The Pile)

Max Activating Token Index: 94