Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 459 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 496602 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1309783 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 830079 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 564846 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0006

Data Index: 567210 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0005

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 593201 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1346090 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 28475 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0006

Data Index: 979354 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 11808 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 211190 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 836791 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 957498 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0081. Min Act: -0.0006

Data Index: 808324 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0006

Data Index: 494421 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0092. Min Act: -0.0006

Data Index: 531740 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1247928 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0006

Data Index: 801438 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0006

Data Index: 378891 (C4 (Web Text))

Max Activating Token Index: 946