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

Dataset: The Pile

Neuron 3316 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: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0000

Data Index: 588771 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.6010. Min Act: -0.0000

Data Index: 975036 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1360976 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1121549 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5630. Min Act: -0.0000

Data Index: 90777 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1894857 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1747000 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5563. Min Act: -0.0000

Data Index: 584135 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1273428 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1593032 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1806089 (The Pile)

Max Activating Token Index: 170

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5106. Min Act: -0.0000

Data Index: 266121 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1090567 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5017. Min Act: -0.0000

Data Index: 69125 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1128496 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1088148 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1395191 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5309. Min Act: -0.0000

Data Index: 554957 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4796. Min Act: -0.0000

Data Index: 224997 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1616603 (The Pile)

Max Activating Token Index: 71