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

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

Neuron 2126 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.5704. Min Act: -0.0000

Data Index: 752218 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4515. Min Act: -0.0000

Data Index: 731512 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1077869 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4128. Min Act: -0.0000

Data Index: 648178 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4428. Min Act: -0.0000

Data Index: 583563 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1194926 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4461. Min Act: -0.0000

Data Index: 988700 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3978. Min Act: -0.0000

Data Index: 782339 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4569. Min Act: -0.0000

Data Index: 278836 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4117. Min Act: -0.0000

Data Index: 648815 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3890. Min Act: -0.0000

Data Index: 213075 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4418. Min Act: -0.0000

Data Index: 718641 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4121. Min Act: -0.0000

Data Index: 131976 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1171541 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3854. Min Act: -0.0000

Data Index: 394570 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1282961 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3767. Min Act: -0.0000

Data Index: 582844 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1334822 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.4023. Min Act: -0.0000

Data Index: 420719 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.5704. Min Range: -0.5704

Max Act: 0.3805. Min Act: -0.0000

Data Index: 977762 (C4 (Web Text))

Max Activating Token Index: 467