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

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

Neuron 932 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0969. Min Act: -0.0001

Data Index: 898837 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0889. Min Act: -0.0001

Data Index: 46937 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0801. Min Act: -0.0001

Data Index: 856001 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0852. Min Act: -0.0001

Data Index: 145003 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1018733 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0787. Min Act: -0.0001

Data Index: 145088 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1254111 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0802. Min Act: -0.0002

Data Index: 548965 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0740. Min Act: -0.0001

Data Index: 245414 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0790. Min Act: -0.0001

Data Index: 534117 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0736. Min Act: -0.0001

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0760. Min Act: -0.0001

Data Index: 887114 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1006472 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1168062 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0699. Min Act: -0.0001

Data Index: 794729 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0688. Min Act: -0.0001

Data Index: 180905 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0718. Min Act: -0.0001

Data Index: 301682 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1110402 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0702. Min Act: -0.0001

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0969. Min Range: -0.0969

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1125543 (C4 (Web Text))

Max Activating Token Index: 87