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

Dataset: The Pile

Neuron 2539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0003

Data Index: 576868 (The Pile)

Max Activating Token Index: 835

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 641848 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1981997 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0003

Data Index: 42722 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0111. Min Act: -0.0003

Data Index: 700701 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0101. Min Act: -0.0003

Data Index: 575824 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1067677 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0079. Min Act: -0.0003

Data Index: 182870 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1675222 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1168119 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1285696 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0079. Min Act: -0.0003

Data Index: 713337 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1652011 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0076. Min Act: -0.0003

Data Index: 663292 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1258007 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0076. Min Act: -0.0003

Data Index: 412754 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0076. Min Act: -0.0003

Data Index: 385106 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0068. Min Act: -0.0003

Data Index: 882596 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1285465 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0073. Min Act: -0.0003

Data Index: 640877 (The Pile)

Max Activating Token Index: 440