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

Dataset: The Pile

Neuron 100 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.1019. Min Act: -0.0000

Data Index: 419548 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0885. Min Act: -0.0000

Data Index: 933284 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1996003 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1466079 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1465189 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1259611 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1641656 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1903500 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1254299 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1934474 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0820. Min Act: -0.0000

Data Index: 58455 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1569226 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1705802 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1612160 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0795. Min Act: -0.0000

Data Index: 522611 (The Pile)

Max Activating Token Index: 318

Text #15

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0800. Min Act: -0.0000

Data Index: 334810 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0795. Min Act: -0.0000

Data Index: 839858 (The Pile)

Max Activating Token Index: 339

Text #17

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1940658 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0791. Min Act: -0.0000

Data Index: 1073983 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 0.1019. Min Range: -0.1019

Max Act: 0.0787. Min Act: -0.0000

Data Index: 253471 (The Pile)

Max Activating Token Index: 167