Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3374 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1293215 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0002

Data Index: 962708 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1353387 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0118. Min Act: -0.0002

Data Index: 836860 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0002

Data Index: 864193 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0118. Min Act: -0.0002

Data Index: 815625 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1168006 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0002

Data Index: 145774 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0115. Min Act: -0.0002

Data Index: 812790 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0122. Min Act: -0.0002

Data Index: 168729 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0117. Min Act: -0.0002

Data Index: 742172 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1077194 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0109. Min Act: -0.0002

Data Index: 118711 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1438353 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1256725 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0092. Min Act: -0.0002

Data Index: 995794 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1149900 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1343293 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0107. Min Act: -0.0002

Data Index: 776691 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0109. Min Act: -0.0002

Data Index: 890827 (C4 (Web Text))

Max Activating Token Index: 512