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

Dataset: The Pile

Neuron 2588 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: 0.9525. Min Range: -0.9525

Max Act: 0.9463. Min Act: -0.0000

Data Index: 584631 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1643304 (The Pile)

Max Activating Token Index: 374

Text #2

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1623280 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1352646 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1441512 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1659390 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7554. Min Act: -0.0000

Data Index: 517024 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1064365 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6937. Min Act: -0.0000

Data Index: 187940 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1740475 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6524. Min Act: -0.0000

Data Index: 215990 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1426075 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1982985 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1066442 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1065014 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6995. Min Act: -0.0000

Data Index: 940076 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1130715 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1824761 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6194. Min Act: -0.0000

Data Index: 720268 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6499. Min Act: -0.0000

Data Index: 577363 (The Pile)

Max Activating Token Index: 428