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

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

Neuron 173 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: 0.0115. Min Act: -0.0006

Data Index: 390062 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0006

Data Index: 136543 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0006

Data Index: 920879 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1525273 (Python Code)

Max Activating Token Index: 188

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1247015 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0096. Min Act: -0.0006

Data Index: 453439 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1119111 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1280914 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0006

Data Index: 808011 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1055265 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0092. Min Act: -0.0006

Data Index: 3806 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0089. Min Act: -0.0006

Data Index: 572371 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0089. Min Act: -0.0006

Data Index: 97546 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0090. Min Act: -0.0006

Data Index: 177513 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0087. Min Act: -0.0006

Data Index: 653459 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0089. Min Act: -0.0006

Data Index: 348516 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0089. Min Act: -0.0006

Data Index: 74652 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0088. Min Act: -0.0006

Data Index: 875464 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1240326 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0085. Min Act: -0.0006

Data Index: 262299 (C4 (Web Text))

Max Activating Token Index: 720