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

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

Neuron 3019 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3019. Min Range: -2.3019

Max Act: 2.3019. Min Act: -0.0000

Data Index: 442544 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.8661. Min Act: -0.0000

Data Index: 789892 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.8378. Min Act: -0.0000

Data Index: 627000 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6946. Min Act: -0.0000

Data Index: 949855 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1333391 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.8641. Min Act: -0.0000

Data Index: 172720 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.7383. Min Act: -0.0000

Data Index: 922673 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.7149. Min Act: -0.0000

Data Index: 724218 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6182. Min Act: -0.0000

Data Index: 1291259 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1269667 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1122703 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6871. Min Act: -0.0000

Data Index: 451524 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6953. Min Act: -0.0000

Data Index: 26989 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6841. Min Act: -0.0000

Data Index: 785462 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6781. Min Act: -0.0000

Data Index: 587936 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6854. Min Act: -0.0000

Data Index: 616793 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.6789. Min Act: -0.0000

Data Index: 1268729 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.5585. Min Act: -0.0000

Data Index: 868507 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.7629. Min Act: -0.0000

Data Index: 874860 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 2.3019. Min Range: -2.3019

Max Act: 1.7561. Min Act: -0.0000

Data Index: 795181 (C4 (Web Text))

Max Activating Token Index: 705