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

Dataset: The Pile

Neuron 1437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.9872. Min Act: -0.0000

Data Index: 647546 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1255112 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.7461. Min Act: -0.0000

Data Index: 73665 (The Pile)

Max Activating Token Index: 799

Text #3

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.6257. Min Act: -0.0000

Data Index: 557118 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.6003. Min Act: -0.0000

Data Index: 619655 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.6842. Min Act: -0.0000

Data Index: 706530 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1662498 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1348405 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5742. Min Act: -0.0000

Data Index: 254485 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5447. Min Act: -0.0000

Data Index: 132650 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5541. Min Act: -0.0000

Data Index: 106496 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1612893 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1718408 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1133796 (The Pile)

Max Activating Token Index: 562

Text #14

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1204673 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.3577. Min Act: -0.0000

Data Index: 300308 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1707996 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1123197 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1395909 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 1.9872. Min Range: -1.9872

Max Act: 1.3716. Min Act: -0.0000

Data Index: 233400 (The Pile)

Max Activating Token Index: 612