Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 749 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0003

Data Index: 48492 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0773. Min Act: -0.0003

Data Index: 413684 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1319182 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1210606 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1191243 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0746. Min Act: -0.0002

Data Index: 280125 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0712. Min Act: -0.0003

Data Index: 931466 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0773. Min Act: -0.0003

Data Index: 566970 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1202461 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0735. Min Act: -0.0003

Data Index: 5394 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0693. Min Act: -0.0003

Data Index: 432577 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0688. Min Act: -0.0003

Data Index: 250802 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0710. Min Act: -0.0003

Data Index: 381956 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0723. Min Act: -0.0003

Data Index: 58664 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0681. Min Act: -0.0003

Data Index: 692987 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0678. Min Act: -0.0003

Data Index: 865052 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0675. Min Act: -0.0003

Data Index: 396113 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1170442 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0706. Min Act: -0.0003

Data Index: 28766 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0671. Min Act: -0.0003

Data Index: 501517 (C4 (Web Text))

Max Activating Token Index: 369