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

Dataset: The Pile

Neuron 2113 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0993. Min Act: -0.0000

Data Index: 924955 (The Pile)

Max Activating Token Index: 149

Text #1

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.1887. Min Act: -0.0000

Data Index: 172217 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0624. Min Act: -0.0000

Data Index: 946408 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0161. Min Act: -0.0000

Data Index: 476221 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1765427 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 1.1887. Min Range: -1.1887

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1804354 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1946536 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1917279 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8732. Min Act: -0.0000

Data Index: 707289 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1887422 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9197. Min Act: -0.0000

Data Index: 961139 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1680060 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1075860 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9591. Min Act: -0.0000

Data Index: 409779 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9350. Min Act: -0.0000

Data Index: 76210 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1769484 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.9096. Min Act: -0.0000

Data Index: 133702 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8586. Min Act: -0.0000

Data Index: 323162 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1832887 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.1887. Min Range: -1.1887

Max Act: 0.8556. Min Act: -0.0000

Data Index: 312838 (The Pile)

Max Activating Token Index: 854