Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5000 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0134. Min Act: -0.0003

Data Index: 894983 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0003

Data Index: 687540 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1214286 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0138. Min Act: -0.0003

Data Index: 589000 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0131. Min Act: -0.0003

Data Index: 279141 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1268901 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1057277 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1218818 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1188101 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0003

Data Index: 687479 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0108. Min Act: -0.0003

Data Index: 496485 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0003

Data Index: 321494 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0003

Data Index: 414423 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0002

Data Index: 64341 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0003

Data Index: 509 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0106. Min Act: -0.0003

Data Index: 580825 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0107. Min Act: -0.0003

Data Index: 537898 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0109. Min Act: -0.0003

Data Index: 796704 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1197354 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0103. Min Act: -0.0003

Data Index: 447547 (C4 (Web Text))

Max Activating Token Index: 69