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

Dataset: The Pile

Neuron 5010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1317773 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1561799 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.2239. Min Act: -0.0000

Data Index: 613417 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1626928 (The Pile)

Max Activating Token Index: 25

Text #4

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1000610 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1324875 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0874. Min Act: -0.0000

Data Index: 880549 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0528. Min Act: 0.0001

Data Index: 1384876 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1687656 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9184. Min Act: 0.0000

Data Index: 808599 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0205. Min Act: -0.0000

Data Index: 279351 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0133. Min Act: -0.0000

Data Index: 445518 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9421. Min Act: 0.0000

Data Index: 178079 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1277644 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0685. Min Act: -0.0000

Data Index: 980920 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1739784 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0143. Min Act: -0.0000

Data Index: 730043 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0016. Min Act: -0.0000

Data Index: 899484 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.3480. Min Range: -1.3480

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1882135 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 1.3480. Min Range: -1.3480

Max Act: 0.8998. Min Act: 0.0000

Data Index: 534333 (The Pile)

Max Activating Token Index: 762