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

Dataset: The Pile

Neuron 1339 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: 0.7172. Min Range: -0.7172

Max Act: 0.7172. Min Act: -0.0000

Data Index: 208581 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1331655 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1347910 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6637. Min Act: -0.0000

Data Index: 500466 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1517278 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6366. Min Act: -0.0000

Data Index: 885670 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.7098. Min Act: -0.0000

Data Index: 373656 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1359562 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6107. Min Act: -0.0000

Data Index: 863811 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6515. Min Act: -0.0000

Data Index: 650744 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6844. Min Act: -0.0000

Data Index: 176928 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6070. Min Act: -0.0000

Data Index: 854852 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6130. Min Act: -0.0000

Data Index: 671619 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6449. Min Act: -0.0000

Data Index: 890391 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1469967 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1276431 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1358279 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.6437. Min Act: -0.0000

Data Index: 959406 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1323973 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.7172. Min Range: -0.7172

Max Act: 0.5887. Min Act: -0.0000

Data Index: 155380 (The Pile)

Max Activating Token Index: 626