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

Dataset: The Pile

Neuron 242 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: 0.1749. Min Range: -0.1749

Max Act: 0.1749. Min Act: -0.0000

Data Index: 620083 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1839112 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1364. Min Act: -0.0000

Data Index: 487196 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1308. Min Act: -0.0000

Data Index: 544449 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1741430 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1195. Min Act: -0.0000

Data Index: 718335 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1217. Min Act: -0.0000

Data Index: 918174 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1137. Min Act: -0.0000

Data Index: 202100 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1716281 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1308970 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1769016 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1077. Min Act: -0.0000

Data Index: 631980 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1630012 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0952. Min Act: -0.0000

Data Index: 512604 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0861. Min Act: -0.0000

Data Index: 321645 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1300649 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1073149 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1766306 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1198535 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.1749. Min Range: -0.1749

Max Act: 0.1039. Min Act: -0.0000

Data Index: 585131 (The Pile)

Max Activating Token Index: 241