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

Dataset: The Pile

Neuron 1835 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: 1.4783. Min Range: -1.4783

Max Act: 1.4783. Min Act: -0.0000

Data Index: 417998 (The Pile)

Max Activating Token Index: 710

Text #1

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.2757. Min Act: -0.0000

Data Index: 187055 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1483345 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1400832 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1605. Min Act: -0.0000

Data Index: 197652 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1797214 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0574. Min Act: -0.0000

Data Index: 130679 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1891. Min Act: -0.0000

Data Index: 84481 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1754878 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9969. Min Act: -0.0000

Data Index: 164234 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0939. Min Act: -0.0000

Data Index: 648678 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0782. Min Act: -0.0000

Data Index: 466246 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0406. Min Act: -0.0000

Data Index: 284243 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1416390 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1100158 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1042592 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1470405 (The Pile)

Max Activating Token Index: 73

Text #17

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1015699 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1065144 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0521. Min Act: -0.0000

Data Index: 25890 (The Pile)

Max Activating Token Index: 158