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

Dataset: The Pile

Neuron 469 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: 0.5339. Min Range: -0.5339

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1755779 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1334492 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4734. Min Act: -0.0000

Data Index: 260658 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1758617 (The Pile)

Max Activating Token Index: 290

Text #4

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4419. Min Act: -0.0000

Data Index: 816517 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4312. Min Act: -0.0000

Data Index: 795025 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4562. Min Act: -0.0000

Data Index: 385002 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1092322 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4008. Min Act: -0.0000

Data Index: 833444 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1625323 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4218. Min Act: -0.0000

Data Index: 349281 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1529069 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1752745 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1759031 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4050. Min Act: -0.0000

Data Index: 201527 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4075. Min Act: -0.0000

Data Index: 350547 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4105. Min Act: -0.0000

Data Index: 1106170 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4267. Min Act: -0.0000

Data Index: 324141 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1005412 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1566125 (The Pile)

Max Activating Token Index: 875