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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1156729 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1354757 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0669. Min Act: -0.0001

Data Index: 816152 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0718. Min Act: -0.0001

Data Index: 717640 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0659. Min Act: -0.0001

Data Index: 908939 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1191366 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1036978 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0607. Min Act: -0.0001

Data Index: 819482 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1206905 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0579. Min Act: -0.0001

Data Index: 569494 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0651. Min Act: -0.0001

Data Index: 836116 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1053722 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0640. Min Act: -0.0001

Data Index: 105553 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0555. Min Act: -0.0001

Data Index: 800962 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1274185 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1187738 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0622. Min Act: -0.0001

Data Index: 386544 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0536. Min Act: -0.0001

Data Index: 134462 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0597. Min Act: -0.0001

Data Index: 463958 (C4 (Web Text))

Max Activating Token Index: 154