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

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

Neuron 996 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5505. Min Range: -4.5505

Max Act: 4.5505. Min Act: -0.0000

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.8884. Min Act: -0.0000

Data Index: 1578030 (Python Code)

Max Activating Token Index: 901

Text #2

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.5092. Min Act: -0.0000

Data Index: 1350633 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1653922 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.3329. Min Act: -0.0000

Data Index: 1432031 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.2585. Min Act: -0.0000

Data Index: 458299 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.2309. Min Act: -0.0000

Data Index: 1436869 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.3333. Min Act: -0.0000

Data Index: 1632701 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.8663. Min Act: -0.0000

Data Index: 1531113 (Python Code)

Max Activating Token Index: 1001

Text #9

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.1191. Min Act: -0.0000

Data Index: 1610966 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.1371. Min Act: -0.0000

Data Index: 1533325 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.9242. Min Act: -0.0000

Data Index: 1436150 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.0759. Min Act: -0.0000

Data Index: 1519859 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.0569. Min Act: -0.0000

Data Index: 1561307 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.0597. Min Act: -0.0000

Data Index: 1616213 (Python Code)

Max Activating Token Index: 715

Text #15

Max Range: 4.5505. Min Range: -4.5505

Max Act: 3.0523. Min Act: -0.0000

Data Index: 1575654 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.8373. Min Act: -0.0000

Data Index: 1556125 (Python Code)

Max Activating Token Index: 945

Text #17

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.9686. Min Act: -0.0000

Data Index: 1561773 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.9709. Min Act: -0.0000

Data Index: 1412910 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 4.5505. Min Range: -4.5505

Max Act: 2.9622. Min Act: -0.0000

Data Index: 1446422 (Python Code)

Max Activating Token Index: 682