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

Dataset: The Pile

Neuron 3320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7058. Min Act: -0.0000

Data Index: 8941 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4202. Min Act: -0.0000

Data Index: 355402 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1287638 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7230. Min Act: -0.0000

Data Index: 449544 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.3227. Min Act: -0.0000

Data Index: 19488 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1969701 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1311907 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1024655 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1057567 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.3242. Min Act: -0.0000

Data Index: 765753 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2800. Min Act: -0.0000

Data Index: 580307 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1643595 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1804178 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2316. Min Act: -0.0000

Data Index: 936806 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2923. Min Act: -0.0000

Data Index: 432832 (The Pile)

Max Activating Token Index: 880

Text #15

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1633402 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2134. Min Act: -0.0000

Data Index: 949949 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1599360 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2304. Min Act: -0.0000

Data Index: 648932 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.2121. Min Act: -0.0000

Data Index: 920170 (The Pile)

Max Activating Token Index: 787