Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1886411 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1329. Min Act: -0.0000

Data Index: 508733 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1321. Min Act: -0.0000

Data Index: 100339 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1604480 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1411128 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1150. Min Act: -0.0000

Data Index: 138476 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1205947 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1194. Min Act: -0.0000

Data Index: 796394 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1155. Min Act: -0.0000

Data Index: 889973 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1190. Min Act: -0.0000

Data Index: 632157 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1600267 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1495981 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1462699 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1018. Min Act: -0.0000

Data Index: 975868 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1084. Min Act: -0.0000

Data Index: 440433 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1547895 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1124240 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1112314 (The Pile)

Max Activating Token Index: 915

Text #18

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1064667 (The Pile)

Max Activating Token Index: 978

Text #19

Max Range: 0.1464. Min Range: -0.1464

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1079746 (The Pile)

Max Activating Token Index: 821