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

Dataset: The Pile

Neuron 333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0000

Data Index: 984581 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0210. Min Act: -0.0000

Data Index: 115398 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0000

Data Index: 1655901 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0185. Min Act: -0.0000

Data Index: 1697823 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0181. Min Act: -0.0000

Data Index: 118875 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0177. Min Act: -0.0000

Data Index: 627384 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0171. Min Act: -0.0000

Data Index: 1885106 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0175. Min Act: -0.0000

Data Index: 1948524 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0175. Min Act: -0.0000

Data Index: 1859704 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1347853 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1143903 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0173. Min Act: -0.0000

Data Index: 750457 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0179. Min Act: -0.0000

Data Index: 663096 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0171. Min Act: -0.0000

Data Index: 51503 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0171. Min Act: -0.0000

Data Index: 1477737 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0171. Min Act: -0.0000

Data Index: 533713 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0164. Min Act: -0.0000

Data Index: 1933132 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0169. Min Act: -0.0000

Data Index: 285292 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0168. Min Act: -0.0000

Data Index: 345299 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0167. Min Act: -0.0000

Data Index: 292453 (The Pile)

Max Activating Token Index: 929