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

Dataset: The Pile

Neuron 4162 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.8793. Min Act: -0.0000

Data Index: 1725740 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1822882 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1585003 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.5460. Min Act: -0.0000

Data Index: 293969 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1143652 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3835. Min Act: -0.0000

Data Index: 170173 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2496. Min Act: -0.0000

Data Index: 544053 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3352. Min Act: -0.0000

Data Index: 68373 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3892. Min Act: -0.0000

Data Index: 221950 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.2824. Min Act: -0.0000

Data Index: 299681 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.3497. Min Act: -0.0000

Data Index: 1577989 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.1818. Min Act: -0.0000

Data Index: 575570 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1789780 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.0369. Min Act: -0.0000

Data Index: 317192 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1281411 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.1600. Min Act: -0.0000

Data Index: 954215 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.8793. Min Range: -1.8793

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1761821 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 1.8793. Min Range: -1.8793

Max Act: 1.0450. Min Act: -0.0000

Data Index: 385372 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 1.8793. Min Range: -1.8793

Max Act: 0.8590. Min Act: -0.0000

Data Index: 458385 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 1.8793. Min Range: -1.8793

Max Act: 0.8422. Min Act: -0.0000

Data Index: 376457 (The Pile)

Max Activating Token Index: 586