Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2785. Min Act: -0.0000

Data Index: 62885 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2688. Min Act: -0.0001

Data Index: 198149 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2672. Min Act: 0.0000

Data Index: 813994 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1044998 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2669. Min Act: -0.0000

Data Index: 745586 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2707. Min Act: -0.0000

Data Index: 297991 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2517. Min Act: -0.0000

Data Index: 669170 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2672. Min Act: -0.0001

Data Index: 964242 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2513. Min Act: -0.0000

Data Index: 34681 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2434. Min Act: -0.0000

Data Index: 247315 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2615. Min Act: -0.0000

Data Index: 771137 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2416. Min Act: -0.0000

Data Index: 976536 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2438. Min Act: -0.0000

Data Index: 111041 (The Pile)

Max Activating Token Index: 700

Text #13

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1110455 (The Pile)

Max Activating Token Index: 776

Text #14

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2325. Min Act: -0.0000

Data Index: 113958 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2466. Min Act: -0.0000

Data Index: 178741 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2457. Min Act: -0.0000

Data Index: 154580 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1713500 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2419. Min Act: -0.0000

Data Index: 324676 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2420. Min Act: -0.0000

Data Index: 202097 (The Pile)

Max Activating Token Index: 182