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

Dataset: The Pile

Neuron 1783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8920. Min Act: -0.0000

Data Index: 868037 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8890. Min Act: -0.0000

Data Index: 1608978 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8012. Min Act: -0.0000

Data Index: 593698 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8083. Min Act: -0.0000

Data Index: 617219 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1890628 (The Pile)

Max Activating Token Index: 496

Text #5

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6090. Min Act: -0.0000

Data Index: 1018592 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.5547. Min Act: -0.0000

Data Index: 1037908 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6394. Min Act: -0.0000

Data Index: 1880852 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.5091. Min Act: -0.0000

Data Index: 396083 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.5228. Min Act: -0.0000

Data Index: 1749445 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.4768. Min Act: -0.0000

Data Index: 356350 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1969692 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1976549 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.5123. Min Act: -0.0000

Data Index: 699424 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.5696. Min Act: -0.0000

Data Index: 1662872 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.2289. Min Act: -0.0000

Data Index: 232454 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.4320. Min Act: -0.0000

Data Index: 298990 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.3378. Min Act: -0.0000

Data Index: 1914726 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1363010 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.2385. Min Act: -0.0000

Data Index: 908861 (The Pile)

Max Activating Token Index: 990