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

Dataset: The Pile

Neuron 2044 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: 1.8660. Min Range: -1.8660

Max Act: 1.8093. Min Act: -0.0000

Data Index: 890781 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8078. Min Act: -0.0000

Data Index: 191386 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8292. Min Act: -0.0000

Data Index: 160972 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1638242 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.8660. Min Act: -0.0000

Data Index: 959984 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1135526 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7198. Min Act: -0.0000

Data Index: 1645362 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1033215 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6735. Min Act: -0.0000

Data Index: 1864273 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7619. Min Act: -0.0000

Data Index: 584341 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5573. Min Act: -0.0000

Data Index: 751037 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.7287. Min Act: -0.0000

Data Index: 935167 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.6525. Min Act: -0.0000

Data Index: 447694 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5227. Min Act: -0.0000

Data Index: 1867278 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5058. Min Act: -0.0000

Data Index: 448965 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5052. Min Act: -0.0000

Data Index: 398855 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1658368 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1854834 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4493. Min Act: -0.0000

Data Index: 596453 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 1.8660. Min Range: -1.8660

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1552426 (The Pile)

Max Activating Token Index: 314