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

Dataset: The Pile

Neuron 2994 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: 3.1093. Min Range: -3.1093

Max Act: 3.1093. Min Act: -0.0000

Data Index: 763333 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 3.1093. Min Range: -3.1093

Max Act: 3.0222. Min Act: -0.0000

Data Index: 339942 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.9914. Min Act: -0.0000

Data Index: 828788 (The Pile)

Max Activating Token Index: 260

Text #3

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.9864. Min Act: -0.0000

Data Index: 1319021 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.9763. Min Act: -0.0000

Data Index: 650579 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8178. Min Act: -0.0000

Data Index: 1784831 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7659. Min Act: -0.0000

Data Index: 1870155 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 3.1093. Min Range: -3.1093

Max Act: 3.0460. Min Act: -0.0000

Data Index: 677975 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 3.1093. Min Range: -3.1093

Max Act: 3.0093. Min Act: -0.0000

Data Index: 1778883 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8659. Min Act: -0.0000

Data Index: 228041 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1427340 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7317. Min Act: -0.0000

Data Index: 1615225 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8330. Min Act: -0.0000

Data Index: 1450404 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.6970. Min Act: -0.0000

Data Index: 1703294 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8237. Min Act: -0.0000

Data Index: 192761 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.6829. Min Act: -0.0000

Data Index: 653437 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8167. Min Act: -0.0000

Data Index: 1665977 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1718836 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7792. Min Act: -0.0000

Data Index: 667027 (The Pile)

Max Activating Token Index: 411

Text #19

Max Range: 3.1093. Min Range: -3.1093

Max Act: 2.7754. Min Act: -0.0000

Data Index: 1153911 (The Pile)

Max Activating Token Index: 312