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

Dataset: The Pile

Neuron 367 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: 0.1461. Min Range: -0.1461

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1000127 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1460. Min Act: -0.0000

Data Index: 274953 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1172993 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1521721 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1413723 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0971. Min Act: -0.0000

Data Index: 172184 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1035465 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1705576 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1225359 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1750706 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0888. Min Act: -0.0000

Data Index: 485180 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1602694 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1432605 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1590792 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1620961 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1701601 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0921. Min Act: -0.0000

Data Index: 430123 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1924176 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0902. Min Act: -0.0000

Data Index: 565058 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1116240 (The Pile)

Max Activating Token Index: 340