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

Dataset: The Pile

Neuron 1908 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1367375 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1865554 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1845398 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1500272 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7120. Min Act: -0.0000

Data Index: 678788 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6660. Min Act: -0.0000

Data Index: 217221 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5743. Min Act: -0.0000

Data Index: 970163 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5485. Min Act: -0.0000

Data Index: 517674 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5391. Min Act: -0.0000

Data Index: 707830 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5487. Min Act: -0.0000

Data Index: 524972 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1021252 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1437457 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.4858. Min Act: -0.0000

Data Index: 343742 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5791. Min Act: -0.0000

Data Index: 313395 (The Pile)

Max Activating Token Index: 174

Text #14

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5912. Min Act: -0.0000

Data Index: 630109 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1084864 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5112. Min Act: -0.0000

Data Index: 140388 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5414. Min Act: -0.0000

Data Index: 344917 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5431. Min Act: -0.0000

Data Index: 702432 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.5119. Min Act: -0.0000

Data Index: 395006 (The Pile)

Max Activating Token Index: 907