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

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

Neuron 4820 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: 2.1088. Min Range: -2.1088

Max Act: 2.1088. Min Act: -0.0000

Data Index: 1099237 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.9530. Min Act: -0.0000

Data Index: 289261 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 2.1088. Min Range: -2.1088

Max Act: 2.0241. Min Act: -0.0000

Data Index: 180235 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.8669. Min Act: -0.0000

Data Index: 1345347 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.6408. Min Act: -0.0000

Data Index: 840805 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4937. Min Act: -0.0000

Data Index: 867641 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.5147. Min Act: -0.0000

Data Index: 37389 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.6826. Min Act: -0.0000

Data Index: 1357734 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.6205. Min Act: -0.0000

Data Index: 134161 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.5550. Min Act: -0.0000

Data Index: 278237 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4955. Min Act: -0.0000

Data Index: 189751 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.3748. Min Act: -0.0000

Data Index: 84960 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4704. Min Act: -0.0000

Data Index: 796823 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.5326. Min Act: -0.0000

Data Index: 1256706 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4888. Min Act: -0.0000

Data Index: 968416 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4819. Min Act: -0.0000

Data Index: 784445 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.3971. Min Act: -0.0000

Data Index: 589640 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1258976 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4609. Min Act: -0.0000

Data Index: 820726 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 2.1088. Min Range: -2.1088

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1056831 (C4 (Web Text))

Max Activating Token Index: 44