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

Dataset: The Pile

Neuron 1879 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: 0.5120. Min Range: -0.5120

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1662869 (The Pile)

Max Activating Token Index: 560

Text #1

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1465321 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4783. Min Act: -0.0000

Data Index: 706166 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4971. Min Act: -0.0000

Data Index: 643968 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4986. Min Act: -0.0000

Data Index: 184046 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1403886 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1810258 (The Pile)

Max Activating Token Index: 434

Text #7

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1552569 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1255569 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1774100 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4316. Min Act: -0.0000

Data Index: 754413 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4423. Min Act: -0.0000

Data Index: 486328 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1303323 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4475. Min Act: -0.0000

Data Index: 878267 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1651658 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4157. Min Act: 0.0000

Data Index: 288877 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4262. Min Act: -0.0000

Data Index: 776146 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4224. Min Act: -0.0000

Data Index: 461439 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1253659 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.5120. Min Range: -0.5120

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1456232 (The Pile)

Max Activating Token Index: 874