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

Dataset: The Pile

Neuron 3571 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: 7.9308. Min Range: -7.9308

Max Act: 7.8542. Min Act: -0.0000

Data Index: 1132210 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.7017. Min Act: -0.0000

Data Index: 1504829 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.5831. Min Act: -0.0000

Data Index: 1973439 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.8145. Min Act: -0.0000

Data Index: 717452 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.7629. Min Act: -0.0000

Data Index: 772042 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.9308. Min Act: -0.0000

Data Index: 1084560 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.4265. Min Act: -0.0000

Data Index: 1086707 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.0985. Min Act: -0.0000

Data Index: 318910 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 7.9308. Min Range: -7.9308

Max Act: 7.4340. Min Act: -0.0000

Data Index: 1674545 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 7.9308. Min Range: -7.9308

Max Act: 5.5751. Min Act: -0.0000

Data Index: 67972 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.9140. Min Act: -0.0000

Data Index: 500757 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 7.9308. Min Range: -7.9308

Max Act: 5.1899. Min Act: -0.0000

Data Index: 1662154 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.6448. Min Act: -0.0000

Data Index: 304550 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.8947. Min Act: -0.0000

Data Index: 840771 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 7.9308. Min Range: -7.9308

Max Act: 5.1105. Min Act: -0.0000

Data Index: 927527 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.3941. Min Act: -0.0000

Data Index: 142268 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.5365. Min Act: -0.0000

Data Index: 1837368 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.9171. Min Act: -0.0000

Data Index: 452850 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.4926. Min Act: -0.0000

Data Index: 205497 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 7.9308. Min Range: -7.9308

Max Act: 4.6518. Min Act: -0.0000

Data Index: 1899686 (The Pile)

Max Activating Token Index: 287