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

Dataset: The Pile

Neuron 2479 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: 1.6345. Min Range: -1.6345

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1196379 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.4737. Min Act: -0.0000

Data Index: 209262 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1861993 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1893222 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1127081 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1219. Min Act: -0.0000

Data Index: 115566 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1295. Min Act: -0.0000

Data Index: 374011 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0525. Min Act: -0.0000

Data Index: 902302 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0629. Min Act: -0.0000

Data Index: 647825 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1785819 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0164. Min Act: -0.0000

Data Index: 328319 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0094. Min Act: -0.0000

Data Index: 426029 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0104. Min Act: -0.0000

Data Index: 615726 (The Pile)

Max Activating Token Index: 495

Text #13

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1543927 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.9478. Min Act: -0.0000

Data Index: 976669 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.9823. Min Act: -0.0000

Data Index: 854378 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.8647. Min Act: 0.0000

Data Index: 1510697 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1289053 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.9056. Min Act: -0.0000

Data Index: 965770 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 1.6345. Min Range: -1.6345

Max Act: 0.9053. Min Act: 0.0000

Data Index: 1937772 (The Pile)

Max Activating Token Index: 676