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

Dataset: The Pile

Neuron 2914 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: 1.7045. Min Range: -1.7045

Max Act: 1.7045. Min Act: -0.0000

Data Index: 839993 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1415207 (The Pile)

Max Activating Token Index: 830

Text #2

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.1896. Min Act: -0.0000

Data Index: 771105 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1515801 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1922740 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0492. Min Act: -0.0000

Data Index: 585050 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1380315 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9835. Min Act: -0.0000

Data Index: 625029 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1524262 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1457941 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0387. Min Act: -0.0000

Data Index: 218253 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0480. Min Act: -0.0000

Data Index: 325120 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0084. Min Act: -0.0000

Data Index: 566783 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1593980 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9835. Min Act: -0.0000

Data Index: 377767 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 1.7045. Min Range: -1.7045

Max Act: 1.0306. Min Act: -0.0000

Data Index: 563232 (The Pile)

Max Activating Token Index: 996

Text #16

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9370. Min Act: -0.0000

Data Index: 730275 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9735. Min Act: -0.0000

Data Index: 726604 (The Pile)

Max Activating Token Index: 243

Text #18

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9103. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 1.7045. Min Range: -1.7045

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1968382 (The Pile)

Max Activating Token Index: 186