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

Dataset: The Pile

Neuron 1064 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: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1502667 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1226. Min Act: -0.0001

Data Index: 149406 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1131. Min Act: -0.0000

Data Index: 205977 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1047. Min Act: -0.0000

Data Index: 684263 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1539392 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1910637 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0800. Min Act: -0.0000

Data Index: 45966 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1904028 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0868. Min Act: -0.0000

Data Index: 982278 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0810. Min Act: -0.0000

Data Index: 276725 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0937. Min Act: -0.0000

Data Index: 108056 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1637836 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0837. Min Act: -0.0000

Data Index: 828396 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1919976 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1975359 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1303492 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0746. Min Act: -0.0000

Data Index: 623952 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0714. Min Act: -0.0000

Data Index: 183519 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1461722 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1088541 (The Pile)

Max Activating Token Index: 894