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

Dataset: The Pile

Neuron 1601 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1726068 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1467770 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1735143 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6326. Min Act: -0.0000

Data Index: 514754 (The Pile)

Max Activating Token Index: 811

Text #4

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5585. Min Act: -0.0000

Data Index: 188912 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5445. Min Act: -0.0000

Data Index: 261651 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1424307 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1973485 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6097. Min Act: -0.0000

Data Index: 293982 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4903. Min Act: -0.0000

Data Index: 525462 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5158. Min Act: -0.0000

Data Index: 740525 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1513927 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4670. Min Act: -0.0000

Data Index: 207447 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1522838 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1504460 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5437. Min Act: -0.0000

Data Index: 161437 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1957076 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1614824 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1487081 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1409087 (The Pile)

Max Activating Token Index: 79