Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2369 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0000

Data Index: 37463 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0928. Min Act: -0.0001

Data Index: 442476 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0893. Min Act: -0.0001

Data Index: 387627 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1029569 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1153284 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0799. Min Act: -0.0001

Data Index: 907494 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0797. Min Act: -0.0001

Data Index: 332834 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0805. Min Act: -0.0000

Data Index: 799367 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0792. Min Act: -0.0000

Data Index: 491477 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0818. Min Act: -0.0001

Data Index: 743470 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1576805 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0782. Min Act: -0.0001

Data Index: 43643 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1157255 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0793. Min Act: -0.0001

Data Index: 845415 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0755. Min Act: -0.0001

Data Index: 826786 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0712. Min Act: -0.0001

Data Index: 540615 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0714. Min Act: -0.0001

Data Index: 524058 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0701. Min Act: -0.0001

Data Index: 187104 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0691. Min Act: -0.0001

Data Index: 582046 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1455557 (Python Code)

Max Activating Token Index: 228