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

Dataset: The Pile

Neuron 1282 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.8412. Min Act: -0.0000

Data Index: 340152 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.7397. Min Act: -0.0000

Data Index: 753932 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1401362 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1607685 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1471447 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5732. Min Act: -0.0000

Data Index: 380742 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1733355 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1596641 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1124971 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4758. Min Act: -0.0000

Data Index: 558467 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5203. Min Act: -0.0000

Data Index: 872702 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1791987 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4599. Min Act: -0.0000

Data Index: 686939 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1120054 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4516. Min Act: -0.0000

Data Index: 998742 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4492. Min Act: -0.0000

Data Index: 321897 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4285. Min Act: -0.0000

Data Index: 460796 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1041936 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4363. Min Act: -0.0000

Data Index: 51514 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.8412. Min Range: -0.8412

Max Act: 0.4667. Min Act: -0.0000

Data Index: 973496 (The Pile)

Max Activating Token Index: 756