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

Dataset: The Pile

Neuron 521 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: 1.8591. Min Range: -1.8591

Max Act: 1.8591. Min Act: -0.0000

Data Index: 493731 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.7176. Min Act: -0.0000

Data Index: 1287819 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.6111. Min Act: -0.0000

Data Index: 1909299 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1222627 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1913628 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1964702 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1898738 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1309524 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1998272 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1976499 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1196220 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.3075. Min Act: -0.0000

Data Index: 990880 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2526. Min Act: -0.0000

Data Index: 34187 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2918. Min Act: -0.0000

Data Index: 142214 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2454. Min Act: -0.0000

Data Index: 952746 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2193. Min Act: -0.0000

Data Index: 540002 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1626608 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1638686 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1940484 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.8591. Min Range: -1.8591

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1626454 (The Pile)

Max Activating Token Index: 379