Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 570 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1056102 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0004

Data Index: 89131 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0004

Data Index: 1089231 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0004

Data Index: 424856 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0004

Data Index: 529825 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0004

Data Index: 596092 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0128. Min Act: -0.0004

Data Index: 908069 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0004

Data Index: 67027 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0126. Min Act: -0.0004

Data Index: 387512 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0004

Data Index: 804280 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 168612 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 1131568 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 297123 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1359636 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 1643071 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 280089 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0004

Data Index: 363205 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 673514 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0004

Data Index: 747416 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0004

Data Index: 518895 (C4 (Web Text))

Max Activating Token Index: 121