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

Dataset: The Pile

Neuron 1451 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: 0.5519. Min Range: -0.5519

Max Act: 0.5519. Min Act: -0.0000

Data Index: 1693781 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1196740 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4394. Min Act: -0.0000

Data Index: 708243 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.4016. Min Act: -0.0000

Data Index: 381038 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3799. Min Act: -0.0000

Data Index: 529290 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1350972 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1795345 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3564. Min Act: -0.0000

Data Index: 96091 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3339. Min Act: -0.0000

Data Index: 905765 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1756193 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1449057 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1074301 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3410. Min Act: -0.0000

Data Index: 838458 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3355. Min Act: -0.0000

Data Index: 611397 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1923925 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1767346 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3448. Min Act: -0.0000

Data Index: 212639 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1282448 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.3512. Min Act: -0.0000

Data Index: 849858 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.5519. Min Range: -0.5519

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1518973 (The Pile)

Max Activating Token Index: 1011