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

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

Neuron 2185 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 936665 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1411464 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1383397 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1454266 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 712109 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1148635 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 728393 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 411685 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0002

Data Index: 735531 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0135. Min Act: -0.0002

Data Index: 974970 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0135. Min Act: -0.0002

Data Index: 395738 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1220246 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1374553 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1367390 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1364082 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1368307 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1389258 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1429467 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1459238 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1430868 (Python Code)

Max Activating Token Index: 1