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

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

Neuron 3774 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0002

Data Index: 66712 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0665. Min Act: -0.0002

Data Index: 142610 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0614. Min Act: -0.0002

Data Index: 446860 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0614. Min Act: -0.0002

Data Index: 812005 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0603. Min Act: -0.0002

Data Index: 865380 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1045351 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0597. Min Act: -0.0002

Data Index: 621748 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0574. Min Act: -0.0002

Data Index: 678005 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0568. Min Act: -0.0002

Data Index: 992673 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0576. Min Act: -0.0002

Data Index: 918876 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0562. Min Act: -0.0002

Data Index: 605080 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1190711 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0572. Min Act: -0.0002

Data Index: 160667 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1203876 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0546. Min Act: -0.0002

Data Index: 776877 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0545. Min Act: -0.0002

Data Index: 938644 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0545. Min Act: -0.0002

Data Index: 626570 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0548. Min Act: -0.0002

Data Index: 646715 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0541. Min Act: -0.0002

Data Index: 839324 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1225501 (C4 (Web Text))

Max Activating Token Index: 3