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

Dataset: The Pile

Neuron 1265 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.6833. Min Act: -0.0000

Data Index: 870599 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5600. Min Act: -0.0000

Data Index: 788968 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1472703 (The Pile)

Max Activating Token Index: 734

Text #3

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1215780 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.5268. Min Act: -0.0000

Data Index: 359555 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1242059 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4773. Min Act: -0.0000

Data Index: 361786 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1927931 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1171388 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1041671 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4487. Min Act: -0.0000

Data Index: 3045 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4644. Min Act: -0.0000

Data Index: 949569 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1397783 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1655710 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1640554 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1892963 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1584654 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4230. Min Act: -0.0000

Data Index: 24735 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4696. Min Act: -0.0000

Data Index: 564951 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.6833. Min Range: -0.6833

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1219551 (The Pile)

Max Activating Token Index: 862