Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 380 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0144. Min Act: -0.0004

Data Index: 49836 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0134. Min Act: -0.0004

Data Index: 542575 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0122. Min Act: -0.0004

Data Index: 481051 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0124. Min Act: -0.0004

Data Index: 796684 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0121. Min Act: -0.0004

Data Index: 390388 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0116. Min Act: -0.0004

Data Index: 898227 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0120. Min Act: -0.0004

Data Index: 611530 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1148306 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1025029 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0117. Min Act: -0.0004

Data Index: 758329 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0115. Min Act: -0.0004

Data Index: 946704 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0117. Min Act: -0.0004

Data Index: 1317045 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0119. Min Act: -0.0004

Data Index: 686186 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0113. Min Act: -0.0004

Data Index: 134082 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0115. Min Act: -0.0004

Data Index: 387077 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0114. Min Act: -0.0004

Data Index: 46704 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0114. Min Act: -0.0004

Data Index: 89548 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1191106 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0113. Min Act: -0.0004

Data Index: 603599 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0144. Min Range: -0.0144

Max Act: 0.0116. Min Act: -0.0004

Data Index: 130147 (C4 (Web Text))

Max Activating Token Index: 785