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

Dataset: The Pile

Neuron 976 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: 1.7639. Min Range: -1.7639

Max Act: 1.7639. Min Act: -0.0000

Data Index: 1324950 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1468270 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.4824. Min Act: -0.0000

Data Index: 665409 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1816075 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1983. Min Act: -0.0000

Data Index: 127417 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.3027. Min Act: -0.0000

Data Index: 66132 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1354291 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.4045. Min Act: -0.0000

Data Index: 309213 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.3035. Min Act: -0.0000

Data Index: 726520 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1937631 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.4725. Min Act: -0.0001

Data Index: 792746 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1108544 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.2609. Min Act: -0.0000

Data Index: 333337 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1658. Min Act: -0.0000

Data Index: 484746 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1600. Min Act: -0.0000

Data Index: 472452 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1335797 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1116. Min Act: -0.0000

Data Index: 247539 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1486208 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 1.7639. Min Range: -1.7639

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1591040 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 1.7639. Min Range: -1.7639

Max Act: 0.9845. Min Act: -0.0000

Data Index: 38982 (The Pile)

Max Activating Token Index: 879