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

Dataset: The Pile

Neuron 4096 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: 5.7177. Min Range: -5.7177

Max Act: 5.3122. Min Act: -0.0000

Data Index: 1433937 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.2068. Min Act: -0.0000

Data Index: 1613839 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.7177. Min Act: -0.0000

Data Index: 126969 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.3911. Min Act: -0.0000

Data Index: 729981 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.1166. Min Act: -0.0000

Data Index: 84250 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.2055. Min Act: -0.0000

Data Index: 1003954 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.9796. Min Act: -0.0000

Data Index: 862119 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.1084. Min Act: -0.0000

Data Index: 1747763 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.9394. Min Act: -0.0000

Data Index: 1774790 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 5.7177. Min Range: -5.7177

Max Act: 5.2811. Min Act: -0.0000

Data Index: 1069183 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.7797. Min Act: -0.0000

Data Index: 955985 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.7159. Min Act: -0.0000

Data Index: 1154355 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.9181. Min Act: -0.0000

Data Index: 1159645 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.8956. Min Act: -0.0000

Data Index: 142357 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.8922. Min Act: -0.0000

Data Index: 914291 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.8434. Min Act: -0.0000

Data Index: 1374244 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.8148. Min Act: -0.0000

Data Index: 439832 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.6354. Min Act: -0.0000

Data Index: 1701980 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.8074. Min Act: -0.0000

Data Index: 17104 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 5.7177. Min Range: -5.7177

Max Act: 4.5179. Min Act: -0.0000

Data Index: 1333923 (The Pile)

Max Activating Token Index: 275