Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.2321. Min Act: -0.0001

Data Index: 663361 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1678. Min Act: -0.0001

Data Index: 583275 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1201. Min Act: -0.0001

Data Index: 660 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9994. Min Act: -0.0001

Data Index: 967112 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.1027. Min Act: -0.0001

Data Index: 345451 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9844. Min Act: -0.0001

Data Index: 373746 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9626. Min Act: -0.0001

Data Index: 135700 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0290. Min Act: -0.0001

Data Index: 270571 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9753. Min Act: -0.0001

Data Index: 179606 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9791. Min Act: -0.0001

Data Index: 274306 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0219. Min Act: -0.0001

Data Index: 937823 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9312. Min Act: -0.0001

Data Index: 6114 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9078. Min Act: -0.0001

Data Index: 1013679 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1016968 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9955. Min Act: -0.0001

Data Index: 323080 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0113. Min Act: -0.0001

Data Index: 542536 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.2321. Min Range: -1.2321

Max Act: 1.0029. Min Act: -0.0001

Data Index: 1292684 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8989. Min Act: -0.0001

Data Index: 976578 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.9149. Min Act: -0.0001

Data Index: 649114 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.2321. Min Range: -1.2321

Max Act: 0.8956. Min Act: -0.0001

Data Index: 981016 (C4 (Web Text))

Max Activating Token Index: 243