Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0785. Min Range: -1.0785

Max Act: 1.0785. Min Act: -0.0001

Data Index: 584482 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.9869. Min Act: -0.0001

Data Index: 616588 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.9768. Min Act: -0.0001

Data Index: 395005 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.9423. Min Act: -0.0001

Data Index: 671327 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.9349. Min Act: -0.0001

Data Index: 598696 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.7962. Min Act: -0.0000

Data Index: 663591 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8876. Min Act: -0.0001

Data Index: 800438 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8789. Min Act: -0.0000

Data Index: 707490 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8366. Min Act: -0.0001

Data Index: 663062 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8600. Min Act: -0.0001

Data Index: 1220232 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8099. Min Act: -0.0001

Data Index: 376325 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8009. Min Act: -0.0000

Data Index: 964037 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8904. Min Act: -0.0000

Data Index: 711523 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8074. Min Act: -0.0001

Data Index: 971073 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8026. Min Act: -0.0001

Data Index: 480292 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.7636. Min Act: -0.0001

Data Index: 841480 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.8163. Min Act: -0.0001

Data Index: 214578 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.7844. Min Act: -0.0001

Data Index: 1249075 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.7639. Min Act: -0.0001

Data Index: 926314 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.0785. Min Range: -1.0785

Max Act: 0.7883. Min Act: -0.0001

Data Index: 1066406 (C4 (Web Text))

Max Activating Token Index: 694