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

Dataset: The Pile

Neuron 3107 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: 0.5797. Min Range: -0.5797

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1353690 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.5061. Min Act: -0.0000

Data Index: 707035 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4888. Min Act: -0.0000

Data Index: 450536 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4821. Min Act: -0.0000

Data Index: 236408 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1898226 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1072119 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1980035 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1089193 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1930863 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4121. Min Act: -0.0000

Data Index: 868026 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1764180 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4459. Min Act: -0.0000

Data Index: 78022 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1251545 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4643. Min Act: -0.0000

Data Index: 41615 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4378. Min Act: -0.0000

Data Index: 414452 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1061851 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4273. Min Act: -0.0000

Data Index: 633164 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1848175 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4424. Min Act: -0.0000

Data Index: 89009 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4670. Min Act: -0.0000

Data Index: 151484 (The Pile)

Max Activating Token Index: 823