Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 924 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1411807 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1408392 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1240994 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1602253 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3210. Min Act: -0.0000

Data Index: 597495 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3184. Min Act: -0.0000

Data Index: 947732 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2741. Min Act: -0.0000

Data Index: 519801 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1636240 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1928902 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2909. Min Act: -0.0000

Data Index: 905024 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3125. Min Act: -0.0000

Data Index: 165813 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1216899 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2792. Min Act: -0.0000

Data Index: 194864 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1238018 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.3114. Min Act: -0.0000

Data Index: 693456 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1299149 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1622946 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1619649 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2762. Min Act: -0.0000

Data Index: 281772 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 0.3766. Min Range: -0.3766

Max Act: 0.2651. Min Act: -0.0000

Data Index: 856548 (The Pile)

Max Activating Token Index: 624