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

Dataset: The Pile

Neuron 3030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.6296. Min Act: -0.0000

Data Index: 598505 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5814. Min Act: -0.0000

Data Index: 954574 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1109090 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5031. Min Act: -0.0000

Data Index: 409044 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1617672 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4710. Min Act: -0.0000

Data Index: 390657 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1528307 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4327. Min Act: -0.0000

Data Index: 411529 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4929. Min Act: -0.0000

Data Index: 884849 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4452. Min Act: -0.0000

Data Index: 64436 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3537. Min Act: -0.0000

Data Index: 995385 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3719. Min Act: -0.0000

Data Index: 720683 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1717405 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1999167 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.4040. Min Act: -0.0000

Data Index: 815584 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1760216 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3504. Min Act: -0.0000

Data Index: 80925 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1875183 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1842890 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.6296. Min Range: -0.6296

Max Act: 0.3199. Min Act: -0.0000

Data Index: 460796 (The Pile)

Max Activating Token Index: 691