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

Dataset: The Pile

Neuron 1508 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: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1033984 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1641. Min Act: -0.0000

Data Index: 172088 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1218722 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1609. Min Act: -0.0000

Data Index: 115030 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1627. Min Act: -0.0000

Data Index: 400870 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1543. Min Act: -0.0000

Data Index: 737335 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1363449 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1783463 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1137685 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1336359 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1413422 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1371. Min Act: -0.0000

Data Index: 674645 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1932695 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1729680 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1241. Min Act: -0.0000

Data Index: 395427 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1535700 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1295328 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1820282 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1642580 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1754200 (The Pile)

Max Activating Token Index: 149