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

Dataset: The Pile

Neuron 2231 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: 0.9856. Min Range: -0.9856

Max Act: 0.9698. Min Act: -0.0000

Data Index: 320093 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1726329 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9750. Min Act: -0.0000

Data Index: 951142 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9630. Min Act: -0.0000

Data Index: 300506 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1028187 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9582. Min Act: -0.0000

Data Index: 461583 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1535883 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9563. Min Act: -0.0000

Data Index: 902639 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1932918 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8526. Min Act: -0.0000

Data Index: 182701 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1364164 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1433029 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1587612 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8669. Min Act: -0.0000

Data Index: 358239 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8517. Min Act: -0.0000

Data Index: 633867 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1869269 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8193. Min Act: -0.0000

Data Index: 906417 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1879109 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1111435 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.9856. Min Range: -0.9856

Max Act: 0.8424. Min Act: -0.0000

Data Index: 290895 (The Pile)

Max Activating Token Index: 336