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

Dataset: The Pile

Neuron 3652 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: 0.6557. Min Range: -0.6557

Max Act: 0.6557. Min Act: -0.0000

Data Index: 1458016 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1376987 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1517948 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5870. Min Act: -0.0000

Data Index: 349892 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1686986 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1157120 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1654398 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1157249 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1571455 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1806511 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5054. Min Act: -0.0000

Data Index: 499854 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4740. Min Act: -0.0000

Data Index: 871672 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1680163 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4922. Min Act: -0.0000

Data Index: 449123 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4725. Min Act: -0.0000

Data Index: 219060 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4677. Min Act: -0.0000

Data Index: 82642 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4878. Min Act: -0.0000

Data Index: 601391 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4544. Min Act: -0.0000

Data Index: 244916 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1587274 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1966342 (The Pile)

Max Activating Token Index: 423