Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2039 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1131683 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3113. Min Act: -0.0000

Data Index: 338858 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1078619 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2039. Min Act: -0.0000

Data Index: 392734 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2082. Min Act: -0.0000

Data Index: 43603 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1710903 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1727. Min Act: -0.0000

Data Index: 466381 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1210341 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1648. Min Act: -0.0000

Data Index: 972947 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1450. Min Act: -0.0000

Data Index: 388154 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1882522 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1873769 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1904374 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1565. Min Act: -0.0000

Data Index: 1958317 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1480. Min Act: -0.0000

Data Index: 61387 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1632. Min Act: -0.0000

Data Index: 949880 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1762213 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1676117 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1448. Min Act: -0.0000

Data Index: 121977 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1227678 (The Pile)

Max Activating Token Index: 815