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

Dataset: The Pile

Neuron 4914 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1362279 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1302468 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.3097. Min Act: -0.0000

Data Index: 577540 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1410926 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1785538 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.1406. Min Act: -0.0000

Data Index: 266528 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.1219. Min Act: -0.0000

Data Index: 143638 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0775. Min Act: -0.0000

Data Index: 983933 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0324. Min Act: -0.0000

Data Index: 367332 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.1182. Min Act: -0.0000

Data Index: 798416 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0712. Min Act: -0.0000

Data Index: 941505 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1469577 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1449109 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.7368. Min Range: -1.7368

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1410685 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1160229 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1864557 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1203536 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.9686. Min Act: -0.0000

Data Index: 284009 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1963341 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 1.7368. Min Range: -1.7368

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1798723 (The Pile)

Max Activating Token Index: 250