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

Dataset: The Pile

Neuron 2576 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: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1644669 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1133. Min Act: -0.0000

Data Index: 229477 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1116. Min Act: -0.0000

Data Index: 81583 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1123093 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1105. Min Act: 0.0000

Data Index: 1438984 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1105. Min Act: -0.0000

Data Index: 585696 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1079. Min Act: 0.0000

Data Index: 1419200 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1064. Min Act: -0.0000

Data Index: 801851 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1060. Min Act: -0.0000

Data Index: 838894 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1866555 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1047. Min Act: 0.0000

Data Index: 1802089 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1046. Min Act: 0.0000

Data Index: 1429686 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1671300 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1015. Min Act: -0.0000

Data Index: 884881 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1685604 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1292959 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0987. Min Act: 0.0000

Data Index: 1264645 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0990. Min Act: -0.0000

Data Index: 856793 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0982. Min Act: -0.0000

Data Index: 831778 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1692492 (The Pile)

Max Activating Token Index: 560