Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 508 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0004

Data Index: 637284 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0110. Min Act: -0.0004

Data Index: 1330746 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0107. Min Act: -0.0004

Data Index: 349023 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0105. Min Act: -0.0005

Data Index: 315064 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0102. Min Act: -0.0005

Data Index: 927947 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1409424 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0094. Min Act: -0.0004

Data Index: 217323 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0093. Min Act: -0.0004

Data Index: 1555510 (Python Code)

Max Activating Token Index: 1001

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0092. Min Act: -0.0005

Data Index: 578919 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0090. Min Act: -0.0004

Data Index: 861396 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0090. Min Act: -0.0004

Data Index: 346405 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0089. Min Act: -0.0004

Data Index: 1400767 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0091. Min Act: -0.0005

Data Index: 326546 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0089. Min Act: -0.0004

Data Index: 1474629 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0089. Min Act: -0.0004

Data Index: 1557528 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0087. Min Act: -0.0004

Data Index: 86634 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0088. Min Act: -0.0004

Data Index: 1422231 (Python Code)

Max Activating Token Index: 187

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0088. Min Act: -0.0005

Data Index: 738986 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0087. Min Act: -0.0004

Data Index: 260275 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0088. Min Act: -0.0004

Data Index: 269773 (C4 (Web Text))

Max Activating Token Index: 816