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

Dataset: The Pile

Neuron 4206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1802171 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1189457 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2690. Min Act: -0.0000

Data Index: 769145 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2784. Min Act: -0.0000

Data Index: 558633 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.3357. Min Act: -0.0000

Data Index: 535054 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1559863 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1556862 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1612388 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2344. Min Act: -0.0000

Data Index: 646935 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1331619 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1593244 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2411. Min Act: -0.0000

Data Index: 839079 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2080. Min Act: -0.0000

Data Index: 96366 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2708. Min Act: -0.0000

Data Index: 792938 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2542. Min Act: -0.0000

Data Index: 769645 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1071012 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1740328 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1228155 (The Pile)

Max Activating Token Index: 884

Text #18

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2417. Min Act: -0.0000

Data Index: 330398 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.3357. Min Range: -0.3357

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1210375 (The Pile)

Max Activating Token Index: 836