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

Dataset: The Pile

Neuron 765 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: 0.3119. Min Range: -0.3119

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1086242 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2824. Min Act: -0.0000

Data Index: 909615 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2989. Min Act: -0.0000

Data Index: 351610 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1322246 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2771. Min Act: -0.0000

Data Index: 471467 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2887. Min Act: -0.0000

Data Index: 723514 (The Pile)

Max Activating Token Index: 556

Text #6

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1212429 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1950403 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2684. Min Act: -0.0000

Data Index: 712237 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1925854 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2606. Min Act: -0.0000

Data Index: 443948 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1730093 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2501. Min Act: -0.0000

Data Index: 23762 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1943464 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2391. Min Act: -0.0000

Data Index: 246187 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2322. Min Act: -0.0000

Data Index: 888909 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1981254 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2409. Min Act: -0.0000

Data Index: 416287 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2375. Min Act: -0.0000

Data Index: 521561 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.3119. Min Range: -0.3119

Max Act: 0.2360. Min Act: -0.0000

Data Index: 460512 (The Pile)

Max Activating Token Index: 870