Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3990 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0003

Data Index: 473751 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0113. Min Act: -0.0003

Data Index: 212077 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0109. Min Act: -0.0003

Data Index: 805285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0003

Data Index: 864332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1347112 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0080. Min Act: -0.0003

Data Index: 16307 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1168453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0075. Min Act: -0.0003

Data Index: 189561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1581489 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0066. Min Act: -0.0004

Data Index: 817121 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1354246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0072. Min Act: -0.0003

Data Index: 781115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0072. Min Act: -0.0003

Data Index: 555358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1333809 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0069. Min Act: -0.0003

Data Index: 208231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0070. Min Act: -0.0004

Data Index: 25876 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1363036 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0064. Min Act: -0.0003

Data Index: 564674 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0066. Min Act: -0.0003

Data Index: 710002 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0068. Min Act: -0.0003

Data Index: 386479 (C4 (Web Text))

Max Activating Token Index: 475