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

Dataset: The Pile

Neuron 2855 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: 1.3856. Min Range: -1.3856

Max Act: 1.3856. Min Act: -0.0000

Data Index: 1289378 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1400588 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.7646. Min Act: -0.0000

Data Index: 993553 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1482141 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1589940 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1963092 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1468420 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.6046. Min Act: -0.0000

Data Index: 407498 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5402. Min Act: -0.0000

Data Index: 420513 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1412034 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1592360 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5740. Min Act: -0.0000

Data Index: 204068 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5679. Min Act: -0.0000

Data Index: 808497 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1557379 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5661. Min Act: -0.0000

Data Index: 555008 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5447. Min Act: -0.0000

Data Index: 97664 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1510937 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1176637 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.4815. Min Act: -0.0000

Data Index: 742099 (The Pile)

Max Activating Token Index: 438

Text #19

Max Range: 1.3856. Min Range: -1.3856

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1364504 (The Pile)

Max Activating Token Index: 323