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

Dataset: The Pile

Neuron 2253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1508. Min Act: -0.0000

Data Index: 287060 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1384. Min Act: -0.0000

Data Index: 633998 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1003371 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1468. Min Act: -0.0000

Data Index: 838265 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1238449 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1331. Min Act: -0.0000

Data Index: 644916 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1625544 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1517171 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1363206 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1390. Min Act: -0.0000

Data Index: 726546 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1459. Min Act: -0.0000

Data Index: 35073 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1528514 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1813670 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1663868 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1064945 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1129171 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1976531 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1393. Min Act: -0.0000

Data Index: 843057 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1106999 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1938964 (The Pile)

Max Activating Token Index: 451