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

Dataset: The Pile

Neuron 3587 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: 4.5256. Min Range: -4.5256

Max Act: 4.5256. Min Act: -0.0000

Data Index: 1388681 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 4.5256. Min Range: -4.5256

Max Act: 4.4677. Min Act: -0.0000

Data Index: 1927949 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.7539. Min Act: -0.0000

Data Index: 468855 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.5554. Min Act: -0.0000

Data Index: 431599 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.6009. Min Act: -0.0000

Data Index: 1965430 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.5772. Min Act: -0.0000

Data Index: 1926584 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.6656. Min Act: -0.0000

Data Index: 8989 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3542. Min Act: -0.0000

Data Index: 1995285 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1201302 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.4750. Min Act: -0.0000

Data Index: 941205 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.2787. Min Act: -0.0000

Data Index: 1398520 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3924. Min Act: -0.0000

Data Index: 145592 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.5362. Min Act: -0.0000

Data Index: 1607910 (The Pile)

Max Activating Token Index: 303

Text #13

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3741. Min Act: -0.0000

Data Index: 1325473 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3649. Min Act: -0.0000

Data Index: 1026047 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.1955. Min Act: -0.0000

Data Index: 309363 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.4891. Min Act: -0.0000

Data Index: 1958258 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3461. Min Act: -0.0000

Data Index: 940468 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.3210. Min Act: -0.0000

Data Index: 305142 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 4.5256. Min Range: -4.5256

Max Act: 3.1690. Min Act: -0.0000

Data Index: 974017 (The Pile)

Max Activating Token Index: 357