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

Dataset: The Pile

Neuron 1134 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: 3.1233. Min Range: -3.1233

Max Act: 3.1095. Min Act: -0.0000

Data Index: 1042113 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1233. Min Act: -0.0000

Data Index: 336391 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9603. Min Act: -0.0000

Data Index: 1023302 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9254. Min Act: -0.0000

Data Index: 1587080 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6836. Min Act: -0.0000

Data Index: 584346 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6544. Min Act: -0.0000

Data Index: 988831 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6417. Min Act: -0.0000

Data Index: 1171223 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.5203. Min Act: -0.0000

Data Index: 646425 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.4762. Min Act: -0.0000

Data Index: 38646 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.1840. Min Act: -0.0000

Data Index: 572255 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2685. Min Act: -0.0000

Data Index: 1839930 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.0739. Min Act: -0.0000

Data Index: 823383 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2711. Min Act: -0.0000

Data Index: 1418386 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.3366. Min Act: -0.0000

Data Index: 54280 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2205. Min Act: -0.0000

Data Index: 665524 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2117. Min Act: -0.0000

Data Index: 792198 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.1681. Min Act: -0.0000

Data Index: 995978 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.1283. Min Act: -0.0000

Data Index: 1825896 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.0113. Min Act: -0.0000

Data Index: 461356 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.0051. Min Act: -0.0000

Data Index: 1508352 (The Pile)

Max Activating Token Index: 656