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

Dataset: The Pile

Neuron 1168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1294580 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1385361 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1565493 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1824. Min Act: -0.0000

Data Index: 444626 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1940. Min Act: -0.0000

Data Index: 912439 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1301316 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1796. Min Act: -0.0000

Data Index: 439821 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1592. Min Act: -0.0000

Data Index: 167025 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1495915 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1786. Min Act: -0.0000

Data Index: 122917 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1374795 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1650. Min Act: -0.0000

Data Index: 386209 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1533. Min Act: -0.0000

Data Index: 663856 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1380. Min Act: -0.0000

Data Index: 980343 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1189560 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1985612 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1500. Min Act: -0.0000

Data Index: 697260 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1394. Min Act: -0.0000

Data Index: 65103 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1624. Min Act: -0.0000

Data Index: 677043 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1216389 (The Pile)

Max Activating Token Index: 351