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

Dataset: The Pile

Neuron 2224 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: 1.0718. Min Range: -1.0718

Max Act: 1.0718. Min Act: -0.0000

Data Index: 587045 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0551. Min Act: -0.0000

Data Index: 434326 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 1.0718. Min Range: -1.0718

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1393360 (The Pile)

Max Activating Token Index: 973

Text #3

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9205. Min Act: -0.0000

Data Index: 826939 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1511888 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9064. Min Act: -0.0000

Data Index: 714626 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9023. Min Act: -0.0000

Data Index: 727031 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1846095 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1134355 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1518422 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8533. Min Act: -0.0000

Data Index: 420904 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8324. Min Act: -0.0000

Data Index: 792775 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8412. Min Act: -0.0000

Data Index: 269005 (The Pile)

Max Activating Token Index: 270

Text #13

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1027472 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8589. Min Act: -0.0000

Data Index: 548880 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1255384 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1500917 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1282881 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1684744 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 1.0718. Min Range: -1.0718

Max Act: 0.8172. Min Act: -0.0000

Data Index: 518288 (The Pile)

Max Activating Token Index: 952