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

Dataset: The Pile

Neuron 908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.6659. Min Act: -0.0000

Data Index: 1095947 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5414. Min Act: -0.0000

Data Index: 372206 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5409. Min Act: -0.0000

Data Index: 804910 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1485653 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.6182. Min Act: -0.0000

Data Index: 44265 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.5169. Min Act: -0.0000

Data Index: 165495 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4851. Min Act: -0.0000

Data Index: 658611 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1871535 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4362. Min Act: -0.0000

Data Index: 901375 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1601057 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1792632 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3952. Min Act: -0.0000

Data Index: 107201 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1331295 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1047185 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1754344 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.4208. Min Act: -0.0000

Data Index: 257487 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3750. Min Act: -0.0000

Data Index: 893467 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3558. Min Act: -0.0000

Data Index: 123977 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3510. Min Act: -0.0000

Data Index: 518168 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 1.6659. Min Range: -1.6659

Max Act: 1.3758. Min Act: -0.0000

Data Index: 104411 (The Pile)

Max Activating Token Index: 880