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

Dataset: The Pile

Neuron 2999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.6075. Min Act: -0.0000

Data Index: 956488 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.4033. Min Act: -0.0000

Data Index: 445554 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.5058. Min Act: -0.0000

Data Index: 1707098 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1675242 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1233407 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1442182 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.2743. Min Act: -0.0000

Data Index: 134899 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1364942 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1297863 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1134452 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0504. Min Act: -0.0000

Data Index: 600755 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1729983 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1530677 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0150. Min Act: -0.0000

Data Index: 1312689 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0982. Min Act: -0.0000

Data Index: 278058 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1462897 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0657. Min Act: -0.0000

Data Index: 519540 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.6075. Min Range: -1.6075

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1196262 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1983544 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 1.6075. Min Range: -1.6075

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1674097 (The Pile)

Max Activating Token Index: 344