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

Dataset: The Pile

Neuron 2080 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8970. Min Act: -0.0000

Data Index: 912982 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1606991 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8087. Min Act: -0.0000

Data Index: 111351 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1951916 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7517. Min Act: -0.0000

Data Index: 491023 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1176031 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1963449 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7521. Min Act: -0.0000

Data Index: 466450 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1949032 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7163. Min Act: -0.0000

Data Index: 900760 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1917324 (The Pile)

Max Activating Token Index: 176

Text #11

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7172. Min Act: -0.0000

Data Index: 99500 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1901272 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1970143 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1949122 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1842074 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1562810 (The Pile)

Max Activating Token Index: 234

Text #17

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1866416 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6587. Min Act: -0.0000

Data Index: 297151 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 0.8970. Min Range: -0.8970

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1840633 (The Pile)

Max Activating Token Index: 765