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

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

Neuron 2519 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.1436. Min Act: -0.0001

Data Index: 1350640 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.1537. Min Act: -0.0001

Data Index: 1051792 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0739. Min Act: -0.0001

Data Index: 841280 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0670. Min Act: -0.0001

Data Index: 659617 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0636. Min Act: -0.0001

Data Index: 473165 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9923. Min Act: -0.0001

Data Index: 561558 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9988. Min Act: -0.0001

Data Index: 381931 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0470. Min Act: -0.0001

Data Index: 17954 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1324660 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9723. Min Act: -0.0001

Data Index: 1012836 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9155. Min Act: -0.0001

Data Index: 200194 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9384. Min Act: -0.0001

Data Index: 1285026 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9798. Min Act: -0.0001

Data Index: 307623 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9565. Min Act: -0.0001

Data Index: 298271 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9914. Min Act: -0.0001

Data Index: 829948 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9769. Min Act: -0.0001

Data Index: 1339864 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.1052. Min Act: -0.0001

Data Index: 389104 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.8307. Min Act: -0.0001

Data Index: 994112 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9378. Min Act: -0.0001

Data Index: 105522 (C4 (Web Text))

Max Activating Token Index: 66