Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 13.6693. Min Range: -13.6693

Max Act: 13.6693. Min Act: -0.0000

Data Index: 683051 (The Pile)

Max Activating Token Index: 132

Text #1

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.9698. Min Act: -0.0000

Data Index: 1075357 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.8497. Min Act: -0.0000

Data Index: 915380 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 13.6693. Min Range: -13.6693

Max Act: 13.4086. Min Act: -0.0000

Data Index: 1635704 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.9567. Min Act: -0.0000

Data Index: 1875156 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.9500. Min Act: -0.0000

Data Index: 890735 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.7832. Min Act: -0.0000

Data Index: 954226 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.7858. Min Act: -0.0000

Data Index: 347221 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.6940. Min Act: -0.0001

Data Index: 982519 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.7631. Min Act: -0.0001

Data Index: 1095860 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.6760. Min Act: -0.0001

Data Index: 970226 (The Pile)

Max Activating Token Index: 170

Text #11

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.4522. Min Act: -0.0000

Data Index: 434846 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.8444. Min Act: -0.0001

Data Index: 1780376 (The Pile)

Max Activating Token Index: 952

Text #13

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.8472. Min Act: -0.0000

Data Index: 1175854 (The Pile)

Max Activating Token Index: 185

Text #14

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.2623. Min Act: -0.0000

Data Index: 207156 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.4799. Min Act: -0.0000

Data Index: 1436088 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.7796. Min Act: -0.0000

Data Index: 350630 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.4056. Min Act: -0.0001

Data Index: 898181 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.4055. Min Act: -0.0001

Data Index: 1671369 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 13.6693. Min Range: -13.6693

Max Act: 12.4800. Min Act: -0.0000

Data Index: 809570 (The Pile)

Max Activating Token Index: 446