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

Dataset: The Pile

Neuron 705 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: 0.6760. Min Range: -0.6760

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1524146 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.6621. Min Act: -0.0000

Data Index: 826191 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.6760. Min Act: -0.0000

Data Index: 967344 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1062716 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5613. Min Act: -0.0000

Data Index: 320258 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1206728 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1425339 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1225307 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1070246 (The Pile)

Max Activating Token Index: 560

Text #9

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1258645 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1310136 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5248. Min Act: -0.0000

Data Index: 862247 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1742318 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5099. Min Act: -0.0000

Data Index: 253968 (The Pile)

Max Activating Token Index: 881

Text #14

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1971950 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1597131 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5103. Min Act: -0.0000

Data Index: 207675 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1351239 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1266550 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 0.6760. Min Range: -0.6760

Max Act: 0.5051. Min Act: -0.0000

Data Index: 348830 (The Pile)

Max Activating Token Index: 888