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

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

Neuron 4977 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: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0000

Data Index: 450507 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6205. Min Act: -0.0000

Data Index: 2147 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1126604 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5095. Min Act: -0.0000

Data Index: 361381 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4906. Min Act: -0.0000

Data Index: 967916 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1121358 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4462. Min Act: -0.0000

Data Index: 371053 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4589. Min Act: -0.0000

Data Index: 430847 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1328077 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4144. Min Act: -0.0000

Data Index: 715948 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4293. Min Act: -0.0000

Data Index: 367053 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1182909 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3944. Min Act: -0.0000

Data Index: 619105 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4214. Min Act: -0.0000

Data Index: 719516 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3833. Min Act: -0.0000

Data Index: 322904 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1177321 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3840. Min Act: -0.0000

Data Index: 878828 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3819. Min Act: -0.0000

Data Index: 512028 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3760. Min Act: -0.0000

Data Index: 138378 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1024252 (C4 (Web Text))

Max Activating Token Index: 983