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

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

Neuron 2903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.5020. Min Act: -0.0002

Data Index: 527973 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4572. Min Act: -0.0002

Data Index: 384607 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4821. Min Act: -0.0002

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4642. Min Act: -0.0002

Data Index: 69406 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1314176 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4658. Min Act: -0.0001

Data Index: 563915 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4598. Min Act: -0.0002

Data Index: 457870 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4729. Min Act: -0.0002

Data Index: 897820 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4567. Min Act: -0.0002

Data Index: 633241 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4550. Min Act: -0.0002

Data Index: 723876 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4539. Min Act: -0.0002

Data Index: 531723 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4349. Min Act: -0.0002

Data Index: 873014 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4469. Min Act: -0.0002

Data Index: 71672 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4154. Min Act: -0.0002

Data Index: 1231535 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4576. Min Act: -0.0002

Data Index: 731709 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4430. Min Act: -0.0001

Data Index: 202387 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4274. Min Act: -0.0002

Data Index: 391938 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4268. Min Act: -0.0002

Data Index: 1208179 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4469. Min Act: -0.0002

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4423. Min Act: -0.0002

Data Index: 450265 (C4 (Web Text))

Max Activating Token Index: 685