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

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

Neuron 1552 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6642. Min Act: -0.0001

Data Index: 276557 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.8100. Min Act: -0.0001

Data Index: 38926 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6736. Min Act: -0.0001

Data Index: 1009508 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6068. Min Act: -0.0001

Data Index: 841594 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6068. Min Act: -0.0001

Data Index: 1010910 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5488. Min Act: -0.0001

Data Index: 1136776 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.4656. Min Act: -0.0001

Data Index: 973607 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.4977. Min Act: -0.0001

Data Index: 78549 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5605. Min Act: -0.0001

Data Index: 857894 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.4191. Min Act: -0.0001

Data Index: 742664 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5074. Min Act: -0.0001

Data Index: 1329733 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5823. Min Act: -0.0001

Data Index: 959457 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5794. Min Act: -0.0001

Data Index: 22564 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.4468. Min Act: -0.0001

Data Index: 845454 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5577. Min Act: -0.0001

Data Index: 603148 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5047. Min Act: -0.0001

Data Index: 269265 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.5584. Min Act: -0.0001

Data Index: 1060919 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.3906. Min Act: -0.0001

Data Index: 481739 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.3886. Min Act: -0.0001

Data Index: 145293 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.3357. Min Act: -0.0001

Data Index: 45241 (C4 (Web Text))

Max Activating Token Index: 285