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

Dataset: The Pile

Neuron 1010 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: 1.8616. Min Range: -1.8616

Max Act: 1.8616. Min Act: -0.0000

Data Index: 1946825 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1874606 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7325. Min Act: -0.0000

Data Index: 349352 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1118561 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5672. Min Act: -0.0000

Data Index: 787468 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1110366 (The Pile)

Max Activating Token Index: 358

Text #6

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5079. Min Act: -0.0000

Data Index: 1226773 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1972622 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5612. Min Act: -0.0000

Data Index: 511780 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1577172 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1030876 (The Pile)

Max Activating Token Index: 716

Text #11

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1519757 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1291185 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1993889 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4387. Min Act: -0.0000

Data Index: 1298020 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4871. Min Act: -0.0000

Data Index: 747240 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1648315 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4561. Min Act: -0.0000

Data Index: 1041696 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1878721 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3054. Min Act: -0.0000

Data Index: 591148 (The Pile)

Max Activating Token Index: 220