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

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

Neuron 1561 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: 2.1787. Min Range: -2.1787

Max Act: 2.1787. Min Act: -0.0000

Data Index: 1104685 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.8054. Min Act: -0.0000

Data Index: 648578 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6511. Min Act: -0.0000

Data Index: 64088 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.6060. Min Act: -0.0000

Data Index: 395469 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1145917 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5358. Min Act: -0.0000

Data Index: 1242502 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5845. Min Act: -0.0000

Data Index: 913393 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1101248 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5234. Min Act: -0.0000

Data Index: 689042 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4179. Min Act: -0.0000

Data Index: 790998 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3875. Min Act: -0.0000

Data Index: 380334 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4351. Min Act: -0.0000

Data Index: 485074 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.5192. Min Act: -0.0000

Data Index: 560273 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.4439. Min Act: -0.0000

Data Index: 180493 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3828. Min Act: -0.0000

Data Index: 967784 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3623. Min Act: -0.0000

Data Index: 879748 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3629. Min Act: -0.0000

Data Index: 55633 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1164486 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2608. Min Act: -0.0000

Data Index: 369947 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 2.1787. Min Range: -2.1787

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1290390 (C4 (Web Text))

Max Activating Token Index: 155