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

Dataset: The Pile

Neuron 1147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.7072. Min Act: -0.0000

Data Index: 842475 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1108588 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6406. Min Act: -0.0000

Data Index: 158326 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6100. Min Act: -0.0000

Data Index: 995709 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1370655 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6092. Min Act: -0.0000

Data Index: 290679 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1729066 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5563. Min Act: -0.0000

Data Index: 712269 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5908. Min Act: -0.0000

Data Index: 689426 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5706. Min Act: -0.0000

Data Index: 338346 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5485. Min Act: -0.0000

Data Index: 744229 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5683. Min Act: -0.0000

Data Index: 993957 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1287097 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1465375 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1146417 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5584. Min Act: -0.0000

Data Index: 926299 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1118685 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5770. Min Act: -0.0000

Data Index: 382984 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5351. Min Act: -0.0000

Data Index: 838562 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1096435 (The Pile)

Max Activating Token Index: 527