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

Dataset: The Pile

Neuron 4914 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: 0.9432. Min Range: -0.9432

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1744137 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1200410 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1627954 (The Pile)

Max Activating Token Index: 474

Text #3

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7819. Min Act: -0.0000

Data Index: 123377 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7660. Min Act: -0.0000

Data Index: 893295 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8131. Min Act: -0.0000

Data Index: 51559 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1085585 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8026. Min Act: -0.0000

Data Index: 841224 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1088598 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1456610 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7666. Min Act: -0.0000

Data Index: 288439 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1078560 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1623334 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1943723 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1883060 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7085. Min Act: -0.0000

Data Index: 805031 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7134. Min Act: -0.0000

Data Index: 472654 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7299. Min Act: -0.0000

Data Index: 680154 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1941615 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1907916 (The Pile)

Max Activating Token Index: 881