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

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

Neuron 2019 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4524. Min Act: -0.0000

Data Index: 940573 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1201059 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1090724 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3967. Min Act: 0.0000

Data Index: 492494 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1123147 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4165. Min Act: -0.0000

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4018. Min Act: 0.0000

Data Index: 1100837 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1231365 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1032724 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3852. Min Act: -0.0000

Data Index: 996933 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3736. Min Act: -0.0000

Data Index: 7538 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3710. Min Act: -0.0000

Data Index: 870278 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1354656 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3642. Min Act: -0.0000

Data Index: 423320 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1315716 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3894. Min Act: -0.0000

Data Index: 866882 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3861. Min Act: -0.0000

Data Index: 465649 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3970. Min Act: 0.0000

Data Index: 888509 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3562. Min Act: -0.0000

Data Index: 979977 (C4 (Web Text))

Max Activating Token Index: 948