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

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

Neuron 4652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0127. Min Range: -1.0127

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1637094 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 1.0127. Min Range: -1.0127

Max Act: 1.0079. Min Act: -0.0000

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1532656 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7982. Min Act: -0.0000

Data Index: 825550 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1088609 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6016. Min Act: -0.0000

Data Index: 566803 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6212. Min Act: -0.0000

Data Index: 883668 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6267. Min Act: -0.0000

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6370. Min Act: -0.0000

Data Index: 874030 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6129. Min Act: -0.0000

Data Index: 679216 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1253961 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5948. Min Act: -0.0000

Data Index: 319955 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1361291 (Python Code)

Max Activating Token Index: 804

Text #13

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1573625 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1450569 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5430. Min Act: -0.0000

Data Index: 801021 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5574. Min Act: -0.0000

Data Index: 82429 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1523421 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1372700 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1471677 (Python Code)

Max Activating Token Index: 481