Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 5 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0005

Data Index: 99756 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0126. Min Act: -0.0005

Data Index: 356550 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0126. Min Act: -0.0005

Data Index: 291774 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1024379 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1559167 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0119. Min Act: -0.0006

Data Index: 807005 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0005

Data Index: 142722 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0118. Min Act: -0.0005

Data Index: 306273 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1427534 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0117. Min Act: -0.0006

Data Index: 377554 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0117. Min Act: -0.0006

Data Index: 562080 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0116. Min Act: -0.0005

Data Index: 656228 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1037138 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0114. Min Act: -0.0005

Data Index: 577244 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1528575 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0114. Min Act: -0.0005

Data Index: 404299 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0114. Min Act: -0.0005

Data Index: 281655 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0113. Min Act: -0.0006

Data Index: 666519 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0113. Min Act: -0.0006

Data Index: 446565 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1134646 (C4 (Web Text))

Max Activating Token Index: 727