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

Dataset: The Pile

Neuron 4673 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1918. Min Range: -4.1918

Max Act: 4.1918. Min Act: -0.0000

Data Index: 520643 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.9210. Min Act: -0.0000

Data Index: 727886 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.8791. Min Act: -0.0000

Data Index: 89707 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.4204. Min Act: -0.0000

Data Index: 1316218 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.4220. Min Act: -0.0000

Data Index: 1649313 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.6147. Min Act: -0.0000

Data Index: 1707293 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5873. Min Act: -0.0000

Data Index: 1761133 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5505. Min Act: -0.0000

Data Index: 229178 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5376. Min Act: -0.0000

Data Index: 830242 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.4882. Min Act: -0.0000

Data Index: 1553311 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.1992. Min Act: -0.0000

Data Index: 282156 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.3032. Min Act: -0.0000

Data Index: 1896261 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.2565. Min Act: -0.0000

Data Index: 910855 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.2339. Min Act: -0.0000

Data Index: 330328 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5002. Min Act: -0.0000

Data Index: 150330 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5486. Min Act: -0.0000

Data Index: 53842 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.5012. Min Act: -0.0000

Data Index: 1026572 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.3401. Min Act: -0.0000

Data Index: 395319 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.3405. Min Act: -0.0000

Data Index: 1704284 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 4.1918. Min Range: -4.1918

Max Act: 3.2607. Min Act: -0.0000

Data Index: 652782 (The Pile)

Max Activating Token Index: 303