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

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

Neuron 1570 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: 0.0780. Min Range: -0.0780

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1166295 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0583. Min Act: -0.0000

Data Index: 993503 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0000

Data Index: 654148 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1139080 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0736. Min Act: -0.0001

Data Index: 683418 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0715. Min Act: -0.0001

Data Index: 166363 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1093467 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0760. Min Act: -0.0000

Data Index: 3749 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1126889 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1167441 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0682. Min Act: -0.0001

Data Index: 610887 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0657. Min Act: -0.0001

Data Index: 449379 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1018458 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1035865 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0676. Min Act: -0.0001

Data Index: 139947 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0617. Min Act: -0.0000

Data Index: 230497 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0605. Min Act: -0.0000

Data Index: 984596 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0626. Min Act: -0.0000

Data Index: 293042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0607. Min Act: -0.0001

Data Index: 12964 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0576. Min Act: -0.0001

Data Index: 609646 (C4 (Web Text))

Max Activating Token Index: 993