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

Dataset: The Pile

Neuron 4103 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.7145. Min Act: -0.0000

Data Index: 1306655 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.4339. Min Act: -0.0000

Data Index: 829001 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.1311. Min Act: -0.0000

Data Index: 806564 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.2073. Min Act: -0.0000

Data Index: 761013 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.0442. Min Act: -0.0000

Data Index: 322830 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.0378. Min Act: -0.0000

Data Index: 591157 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9989. Min Act: -0.0000

Data Index: 303005 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1844567 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9839. Min Act: -0.0000

Data Index: 158962 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1294498 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1392062 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9627. Min Act: -0.0000

Data Index: 253916 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 1.7145. Min Range: -1.7145

Max Act: 1.0590. Min Act: -0.0000

Data Index: 827804 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.9242. Min Act: -0.0000

Data Index: 109161 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8923. Min Act: -0.0000

Data Index: 264469 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1824437 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1933701 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8773. Min Act: -0.0000

Data Index: 444442 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8659. Min Act: -0.0000

Data Index: 675582 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.7145. Min Range: -1.7145

Max Act: 0.8907. Min Act: -0.0000

Data Index: 97353 (The Pile)

Max Activating Token Index: 722