Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2317 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0003

Data Index: 632376 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0112. Min Act: -0.0003

Data Index: 319893 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1091747 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1282146 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1352619 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0088. Min Act: -0.0003

Data Index: 974909 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1282548 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0092. Min Act: -0.0003

Data Index: 411009 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0090. Min Act: -0.0003

Data Index: 386361 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0086. Min Act: -0.0003

Data Index: 844081 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0089. Min Act: -0.0003

Data Index: 163208 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0089. Min Act: -0.0003

Data Index: 635549 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0083. Min Act: -0.0003

Data Index: 147404 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0087. Min Act: -0.0003

Data Index: 963326 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0078. Min Act: -0.0003

Data Index: 946626 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1328774 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0080. Min Act: -0.0003

Data Index: 458246 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1051160 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1110049 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0083. Min Act: -0.0003

Data Index: 644660 (C4 (Web Text))

Max Activating Token Index: 391