Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1973 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9083. Min Act: -0.0001

Data Index: 626319 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8582. Min Act: -0.0001

Data Index: 341007 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.9023. Min Act: -0.0001

Data Index: 40804 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8366. Min Act: -0.0001

Data Index: 379278 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8120. Min Act: -0.0001

Data Index: 293734 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7786. Min Act: -0.0001

Data Index: 327824 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7768. Min Act: -0.0001

Data Index: 1141127 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7858. Min Act: -0.0001

Data Index: 1067073 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7799. Min Act: 0.0000

Data Index: 515885 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.8088. Min Act: -0.0001

Data Index: 28450 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7827. Min Act: -0.0001

Data Index: 86523 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7392. Min Act: -0.0001

Data Index: 1175547 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7504. Min Act: -0.0001

Data Index: 698631 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1046801 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7250. Min Act: -0.0001

Data Index: 1172175 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7214. Min Act: -0.0000

Data Index: 857157 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7193. Min Act: -0.0001

Data Index: 633617 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7407. Min Act: -0.0001

Data Index: 405819 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1075143 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.9083. Min Range: -0.9083

Max Act: 0.7152. Min Act: -0.0001

Data Index: 458587 (C4 (Web Text))

Max Activating Token Index: 757