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

Dataset: The Pile

Neuron 2193 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1664367 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5148. Min Act: -0.0000

Data Index: 229596 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1233658 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1725208 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4876. Min Act: -0.0000

Data Index: 357665 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1781663 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1027803 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1971854 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1835228 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1985728 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4835. Min Act: -0.0000

Data Index: 500082 (The Pile)

Max Activating Token Index: 481

Text #11

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1783307 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4217. Min Act: -0.0000

Data Index: 182207 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4600. Min Act: -0.0000

Data Index: 8684 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4467. Min Act: -0.0000

Data Index: 585038 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1677059 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1671990 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1045642 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4431. Min Act: -0.0000

Data Index: 66519 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 0.5821. Min Range: -0.5821

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1735131 (The Pile)

Max Activating Token Index: 931