Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.9538. Min Act: -0.0000

Data Index: 462491 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8073. Min Act: -0.0000

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.8133. Min Act: -0.0000

Data Index: 94559 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7764. Min Act: -0.0000

Data Index: 468235 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7199. Min Act: -0.0000

Data Index: 616657 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7530. Min Act: -0.0000

Data Index: 916178 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7286. Min Act: -0.0000

Data Index: 755317 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1251683 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7243. Min Act: -0.0000

Data Index: 172062 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7002. Min Act: -0.0000

Data Index: 612887 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1532907 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6725. Min Act: -0.0000

Data Index: 393048 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7148. Min Act: -0.0000

Data Index: 126281 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6815. Min Act: -0.0000

Data Index: 987638 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1243793 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1055150 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6743. Min Act: -0.0000

Data Index: 105001 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6736. Min Act: -0.0000

Data Index: 460044 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6997. Min Act: -0.0000

Data Index: 159459 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.9538. Min Range: -0.9538

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1037034 (C4 (Web Text))

Max Activating Token Index: 653