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

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

Neuron 677 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5695. Min Act: -0.0000

Data Index: 887648 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5621. Min Act: -0.0000

Data Index: 69293 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5233. Min Act: -0.0000

Data Index: 516146 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5449. Min Act: -0.0000

Data Index: 351583 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1355114 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4760. Min Act: -0.0000

Data Index: 554098 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4596. Min Act: -0.0000

Data Index: 799193 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1201218 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4411. Min Act: -0.0001

Data Index: 380359 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4733. Min Act: -0.0001

Data Index: 871656 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1205070 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4444. Min Act: -0.0000

Data Index: 661556 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3975. Min Act: -0.0000

Data Index: 469876 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3967. Min Act: -0.0000

Data Index: 904081 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1346908 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4080. Min Act: -0.0000

Data Index: 948902 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3953. Min Act: -0.0000

Data Index: 511717 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3782. Min Act: -0.0000

Data Index: 924267 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3871. Min Act: -0.0001

Data Index: 796642 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.3897. Min Act: -0.0000

Data Index: 713781 (C4 (Web Text))

Max Activating Token Index: 214