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

Dataset: The Pile

Neuron 283 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: 0.1764. Min Range: -0.1764

Max Act: 0.1732. Min Act: -0.0000

Data Index: 279586 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1632815 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1540980 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1041450 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1496489 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1155863 (The Pile)

Max Activating Token Index: 639

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1351175 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1515721 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1576. Min Act: -0.0000

Data Index: 454681 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1312341 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1905756 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1565. Min Act: -0.0000

Data Index: 229436 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1690. Min Act: -0.0000

Data Index: 804722 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1544. Min Act: -0.0000

Data Index: 476014 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1714683 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1456. Min Act: -0.0000

Data Index: 488799 (The Pile)

Max Activating Token Index: 500

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1548. Min Act: 0.0000

Data Index: 796094 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1869188 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1385337 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1965415 (The Pile)

Max Activating Token Index: 699