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

Dataset: The Pile

Neuron 4810 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2859. Min Act: -0.0000

Data Index: 676400 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2554. Min Act: -0.0000

Data Index: 798617 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1713887 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2710. Min Act: -0.0000

Data Index: 22585 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2349. Min Act: -0.0000

Data Index: 944231 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2401. Min Act: -0.0000

Data Index: 875062 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1174468 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1648854 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1721907 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1666599 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1046884 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1270101 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2242. Min Act: -0.0000

Data Index: 917471 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2110. Min Act: -0.0000

Data Index: 148785 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1874933 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2180. Min Act: -0.0000

Data Index: 142423 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1128131 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2151. Min Act: -0.0000

Data Index: 373202 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1852414 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2001. Min Act: -0.0000

Data Index: 805958 (The Pile)

Max Activating Token Index: 132