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

Dataset: The Pile

Neuron 911 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5917. Min Act: -0.0000

Data Index: 849323 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1652902 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.6021. Min Act: -0.0000

Data Index: 749236 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5511. Min Act: 0.0000

Data Index: 1458297 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5106. Min Act: -0.0000

Data Index: 284378 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1865514 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1292283 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1164575 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4714. Min Act: 0.0000

Data Index: 1367370 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1551767 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4750. Min Act: 0.0000

Data Index: 735620 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4927. Min Act: -0.0000

Data Index: 945820 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4616. Min Act: 0.0000

Data Index: 657287 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4274. Min Act: -0.0000

Data Index: 33087 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4472. Min Act: -0.0000

Data Index: 843297 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4486. Min Act: 0.0000

Data Index: 1548247 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4449. Min Act: -0.0000

Data Index: 773357 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4408. Min Act: -0.0000

Data Index: 235074 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1304437 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.6033. Min Range: -0.6033

Max Act: 0.4359. Min Act: -0.0000

Data Index: 42880 (The Pile)

Max Activating Token Index: 299