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

Dataset: The Pile

Neuron 2689 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.3695. Min Act: -0.0000

Data Index: 135219 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1684734 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1496726 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1754171 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2431. Min Act: 0.0000

Data Index: 837463 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2701. Min Act: -0.0000

Data Index: 753454 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1197843 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2526. Min Act: -0.0000

Data Index: 426666 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1303076 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2562. Min Act: -0.0000

Data Index: 207337 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1943852 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2428. Min Act: -0.0000

Data Index: 52956 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2497. Min Act: -0.0000

Data Index: 200997 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2413. Min Act: -0.0000

Data Index: 530217 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1402397 (The Pile)

Max Activating Token Index: 290

Text #15

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1281666 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1426555 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1961952 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2373. Min Act: -0.0000

Data Index: 349841 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 0.3695. Min Range: -0.3695

Max Act: 0.2422. Min Act: -0.0000

Data Index: 828611 (The Pile)

Max Activating Token Index: 623