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

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

Neuron 2447 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0118. Min Act: -0.0004

Data Index: 208573 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0116. Min Act: -0.0003

Data Index: 527737 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0108. Min Act: -0.0004

Data Index: 839167 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0003

Data Index: 386727 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0003

Data Index: 404766 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0094. Min Act: -0.0003

Data Index: 680668 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0094. Min Act: -0.0004

Data Index: 1153306 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0091. Min Act: -0.0004

Data Index: 1157570 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1169761 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0091. Min Act: -0.0003

Data Index: 607157 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0090. Min Act: -0.0003

Data Index: 228757 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0086. Min Act: -0.0003

Data Index: 573923 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1408315 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0087. Min Act: -0.0003

Data Index: 478185 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0087. Min Act: -0.0003

Data Index: 536764 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0089. Min Act: -0.0003

Data Index: 362259 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0085. Min Act: -0.0003

Data Index: 94908 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0088. Min Act: -0.0003

Data Index: 733668 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0087. Min Act: -0.0003

Data Index: 420546 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0086. Min Act: -0.0003

Data Index: 308351 (C4 (Web Text))

Max Activating Token Index: 512