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

Dataset: The Pile

Neuron 1748 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: 0.6849. Min Range: -0.6849

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1471798 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6703. Min Act: -0.0000

Data Index: 883497 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1715886 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6849. Min Act: -0.0000

Data Index: 654555 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1084525 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6362. Min Act: -0.0000

Data Index: 456583 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.6121. Min Act: -0.0000

Data Index: 469052 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5337. Min Act: -0.0000

Data Index: 64887 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1350552 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1516044 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1059766 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4797. Min Act: -0.0000

Data Index: 264326 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5508. Min Act: -0.0000

Data Index: 478377 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1905574 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.5152. Min Act: -0.0000

Data Index: 309010 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1852276 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4601. Min Act: -0.0000

Data Index: 205838 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4312. Min Act: -0.0000

Data Index: 387220 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4177. Min Act: -0.0000

Data Index: 332086 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 0.6849. Min Range: -0.6849

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1395988 (The Pile)

Max Activating Token Index: 1014