Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1083 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0005

Data Index: 1415652 (Python Code)

Max Activating Token Index: 529

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1165. Min Act: -0.0005

Data Index: 1629202 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1083. Min Act: -0.0005

Data Index: 42183 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1185. Min Act: -0.0005

Data Index: 1362342 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1138. Min Act: -0.0005

Data Index: 1386485 (Python Code)

Max Activating Token Index: 739

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1122. Min Act: -0.0005

Data Index: 793741 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1110. Min Act: -0.0005

Data Index: 968228 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1082. Min Act: -0.0005

Data Index: 1642768 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1062. Min Act: -0.0005

Data Index: 1613349 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1050. Min Act: -0.0005

Data Index: 545064 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1067. Min Act: -0.0005

Data Index: 1475925 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1025. Min Act: -0.0005

Data Index: 1527738 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1057. Min Act: -0.0005

Data Index: 1403145 (Python Code)

Max Activating Token Index: 650

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1019. Min Act: -0.0005

Data Index: 1535987 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1043. Min Act: -0.0005

Data Index: 1510756 (Python Code)

Max Activating Token Index: 729

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1084. Min Act: -0.0005

Data Index: 1548422 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1021. Min Act: -0.0005

Data Index: 503328 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1002. Min Act: -0.0005

Data Index: 1389491 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1033. Min Act: -0.0005

Data Index: 69559 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1031. Min Act: -0.0005

Data Index: 1485499 (Python Code)

Max Activating Token Index: 658