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

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

Neuron 1088 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.8727. Min Act: -0.0001

Data Index: 601437 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7952. Min Act: -0.0001

Data Index: 1090715 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.9451. Min Act: -0.0001

Data Index: 188425 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7548. Min Act: -0.0001

Data Index: 296954 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.8326. Min Act: -0.0001

Data Index: 221919 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7472. Min Act: -0.0001

Data Index: 382829 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7360. Min Act: -0.0001

Data Index: 1162945 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6645. Min Act: -0.0001

Data Index: 591420 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6965. Min Act: -0.0001

Data Index: 163408 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6070. Min Act: -0.0001

Data Index: 500883 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6965. Min Act: -0.0001

Data Index: 1313743 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7939. Min Act: -0.0001

Data Index: 374060 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7073. Min Act: -0.0001

Data Index: 907001 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6456. Min Act: -0.0001

Data Index: 393307 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6491. Min Act: -0.0001

Data Index: 180274 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.7853. Min Act: -0.0001

Data Index: 782703 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.5722. Min Act: -0.0001

Data Index: 62075 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.4953. Min Act: -0.0001

Data Index: 998503 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.4962. Min Act: -0.0000

Data Index: 971110 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.9451. Min Range: -1.9451

Max Act: 1.6531. Min Act: -0.0001

Data Index: 221600 (C4 (Web Text))

Max Activating Token Index: 364