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

Dataset: The Pile

Neuron 756 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: 0.1969. Min Range: -0.1969

Max Act: 0.1931. Min Act: -0.0000

Data Index: 761106 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1904931 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1715965 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1121336 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1693240 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1221932 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1162296 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1258223 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1782220 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1125538 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1678514 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1178. Min Act: -0.0000

Data Index: 641788 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1731245 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1158. Min Act: -0.0000

Data Index: 506774 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1633321 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1112. Min Act: -0.0000

Data Index: 684875 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1943583 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1246. Min Act: -0.0000

Data Index: 85704 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1074291 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.1969. Min Range: -0.1969

Max Act: 0.1063. Min Act: -0.0000

Data Index: 266109 (The Pile)

Max Activating Token Index: 198