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

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

Neuron 2665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.3657. Min Act: -0.0000

Data Index: 640048 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.2243. Min Act: -0.0000

Data Index: 708863 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1069228 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1019622 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9990. Min Act: -0.0000

Data Index: 379797 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.0285. Min Act: -0.0000

Data Index: 869761 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1594628 (Python Code)

Max Activating Token Index: 775

Text #7

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9973. Min Act: -0.0000

Data Index: 368370 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1043670 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.0604. Min Act: -0.0000

Data Index: 758016 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9854. Min Act: -0.0000

Data Index: 309453 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9340. Min Act: -0.0000

Data Index: 923746 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.8704. Min Act: -0.0000

Data Index: 45400 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9148. Min Act: -0.0000

Data Index: 61837 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.3657. Min Range: -1.3657

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1465173 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1650165 (Python Code)

Max Activating Token Index: 859

Text #16

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.8933. Min Act: -0.0000

Data Index: 561853 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1585250 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1089401 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.3657. Min Range: -1.3657

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1165753 (C4 (Web Text))

Max Activating Token Index: 294