Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0495. Min Range: -1.0495

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1166819 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1475458 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1695850 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1563633 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7710. Min Act: -0.0000

Data Index: 468020 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7591. Min Act: -0.0000

Data Index: 720533 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7378. Min Act: -0.0000

Data Index: 791050 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6947. Min Act: -0.0000

Data Index: 298624 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1700793 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6563. Min Act: -0.0000

Data Index: 745797 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1506026 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1123120 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6783. Min Act: -0.0000

Data Index: 117664 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6229. Min Act: -0.0000

Data Index: 879453 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1132708 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1413751 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1699937 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.6425. Min Act: -0.0000

Data Index: 52945 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5982. Min Act: -0.0000

Data Index: 681517 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1534030 (The Pile)

Max Activating Token Index: 813