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

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

Neuron 1641 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: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0006

Data Index: 553866 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0114. Min Act: -0.0006

Data Index: 561132 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0006

Data Index: 719322 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0087. Min Act: -0.0006

Data Index: 248190 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1282055 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0084. Min Act: -0.0006

Data Index: 114745 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0084. Min Act: -0.0006

Data Index: 733776 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1219621 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0082. Min Act: -0.0006

Data Index: 250955 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0083. Min Act: -0.0006

Data Index: 331757 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0081. Min Act: -0.0006

Data Index: 354115 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0082. Min Act: -0.0006

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0081. Min Act: -0.0005

Data Index: 67820 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0080. Min Act: -0.0006

Data Index: 735045 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0080. Min Act: -0.0006

Data Index: 58891 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1271212 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0077. Min Act: -0.0006

Data Index: 225795 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0078. Min Act: -0.0006

Data Index: 605261 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0075. Min Act: -0.0006

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0076. Min Act: -0.0006

Data Index: 251824 (C4 (Web Text))

Max Activating Token Index: 789