Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2177 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0002

Data Index: 844268 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0101. Min Act: -0.0003

Data Index: 182610 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0090. Min Act: -0.0003

Data Index: 227952 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0087. Min Act: -0.0003

Data Index: 780236 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0078. Min Act: -0.0003

Data Index: 253354 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1458188 (Python Code)

Max Activating Token Index: 746

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0079. Min Act: -0.0002

Data Index: 687039 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0075. Min Act: -0.0002

Data Index: 245314 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1430933 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1369482 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1361765 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1460480 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1416247 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0069. Min Act: -0.0003

Data Index: 934642 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1629639 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0072. Min Act: -0.0002

Data Index: 1486401 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0073. Min Act: -0.0003

Data Index: 928947 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1338216 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0070. Min Act: -0.0002

Data Index: 872062 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1261556 (C4 (Web Text))

Max Activating Token Index: 510