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

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

Neuron 1367 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6360. Min Act: -0.0001

Data Index: 705970 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1225450 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6430. Min Act: -0.0001

Data Index: 629196 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6468. Min Act: -0.0001

Data Index: 240681 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6245. Min Act: -0.0001

Data Index: 543649 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6293. Min Act: -0.0001

Data Index: 966691 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6210. Min Act: -0.0001

Data Index: 980238 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6262. Min Act: -0.0001

Data Index: 1258007 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6204. Min Act: -0.0001

Data Index: 759605 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6305. Min Act: -0.0001

Data Index: 696967 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5748. Min Act: -0.0001

Data Index: 693659 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6030. Min Act: -0.0001

Data Index: 712788 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5608. Min Act: -0.0001

Data Index: 866989 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5873. Min Act: -0.0001

Data Index: 563370 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5715. Min Act: -0.0001

Data Index: 767250 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5681. Min Act: -0.0001

Data Index: 1299525 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5658. Min Act: -0.0001

Data Index: 949369 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5657. Min Act: -0.0001

Data Index: 990323 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5833. Min Act: -0.0001

Data Index: 793058 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5284. Min Act: -0.0001

Data Index: 675654 (C4 (Web Text))

Max Activating Token Index: 230