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

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

Neuron 1807 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0004

Data Index: 921013 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0004

Data Index: 174657 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0004

Data Index: 1181203 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 481045 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0003

Data Index: 645081 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 178247 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0004

Data Index: 1077884 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0003

Data Index: 303452 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0004

Data Index: 574520 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1110719 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0004

Data Index: 496128 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0004

Data Index: 221646 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0003

Data Index: 528342 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0100. Min Act: -0.0003

Data Index: 815223 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0004

Data Index: 685837 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0004

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0004

Data Index: 697306 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0004

Data Index: 604907 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0101. Min Act: -0.0003

Data Index: 594783 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0098. Min Act: -0.0003

Data Index: 956456 (C4 (Web Text))

Max Activating Token Index: 756