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

Dataset: The Pile

Neuron 3568 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.1266. Min Act: -0.0000

Data Index: 1997268 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1323648 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1941990 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.1491. Min Act: -0.0000

Data Index: 523625 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 1.1945. Min Range: -1.1945

Max Act: 1.0643. Min Act: -0.0000

Data Index: 569812 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9619. Min Act: -0.0000

Data Index: 507945 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1794911 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1504885 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9943. Min Act: -0.0000

Data Index: 274629 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9159. Min Act: -0.0000

Data Index: 111621 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9602. Min Act: 0.0000

Data Index: 1107588 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8239. Min Act: -0.0000

Data Index: 856135 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1389728 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1532123 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9147. Min Act: 0.0001

Data Index: 1638142 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.9015. Min Act: -0.0000

Data Index: 100931 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1458880 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7977. Min Act: -0.0000

Data Index: 182348 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.7936. Min Act: 0.0000

Data Index: 675363 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 1.1945. Min Range: -1.1945

Max Act: 0.8878. Min Act: -0.0000

Data Index: 902640 (The Pile)

Max Activating Token Index: 879