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

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

Neuron 208 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: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 477489 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0004

Data Index: 795877 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0069. Min Act: -0.0004

Data Index: 1315528 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0004

Data Index: 475800 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0004

Data Index: 1161697 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0004

Data Index: 1329769 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0004

Data Index: 642311 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0004

Data Index: 979686 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0004

Data Index: 1157861 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0004

Data Index: 795348 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1237040 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1071292 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0073. Min Act: -0.0004

Data Index: 1012708 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0004

Data Index: 838123 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0070. Min Act: -0.0004

Data Index: 74404 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0061. Min Act: -0.0004

Data Index: 401234 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0072. Min Act: -0.0004

Data Index: 459170 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0061. Min Act: -0.0004

Data Index: 577164 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0063. Min Act: -0.0004

Data Index: 1292714 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0063. Min Act: -0.0004

Data Index: 553647 (C4 (Web Text))

Max Activating Token Index: 885