Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2074 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0004

Data Index: 378819 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0147. Min Act: -0.0004

Data Index: 1113580 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0138. Min Act: -0.0004

Data Index: 832595 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0127. Min Act: -0.0004

Data Index: 225809 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0127. Min Act: -0.0004

Data Index: 143587 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0127. Min Act: -0.0004

Data Index: 1196123 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0111. Min Act: -0.0004

Data Index: 905450 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0004

Data Index: 229533 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1137014 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0121. Min Act: -0.0004

Data Index: 7511 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0004

Data Index: 771202 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1127257 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0004

Data Index: 857318 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0115. Min Act: -0.0004

Data Index: 757066 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1130284 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0004

Data Index: 801166 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0110. Min Act: -0.0004

Data Index: 269468 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0109. Min Act: -0.0004

Data Index: 553979 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0109. Min Act: -0.0004

Data Index: 200985 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0112. Min Act: -0.0004

Data Index: 158471 (C4 (Web Text))

Max Activating Token Index: 330