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

Dataset: The Pile

Neuron 395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6820. Min Act: -0.0000

Data Index: 1643595 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.5868. Min Act: -0.0000

Data Index: 364803 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1904298 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.5948. Min Act: -0.0000

Data Index: 1072816 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.5702. Min Act: -0.0000

Data Index: 824462 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.6083. Min Act: -0.0000

Data Index: 501611 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1301146 (The Pile)

Max Activating Token Index: 856

Text #7

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.5364. Min Act: -0.0000

Data Index: 184559 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3590. Min Act: -0.0000

Data Index: 870331 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4327. Min Act: -0.0000

Data Index: 373919 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.4145. Min Act: -0.0000

Data Index: 370386 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1761257 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3868. Min Act: -0.0000

Data Index: 830714 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1875539 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3493. Min Act: -0.0000

Data Index: 480677 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1499843 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1852797 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.2492. Min Act: -0.0000

Data Index: 623138 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3208. Min Act: -0.0000

Data Index: 821832 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 1.6820. Min Range: -1.6820

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1427592 (The Pile)

Max Activating Token Index: 689