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

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

Neuron 4735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6008. Min Range: -2.6008

Max Act: 2.6008. Min Act: -0.0000

Data Index: 978222 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 2.6008. Min Range: -2.6008

Max Act: 2.3776. Min Act: -0.0000

Data Index: 1276018 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.6569. Min Act: -0.0000

Data Index: 247413 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.7263. Min Act: -0.0000

Data Index: 53426 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.7203. Min Act: -0.0000

Data Index: 80092 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1186449 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.7063. Min Act: -0.0000

Data Index: 527374 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.6992. Min Act: -0.0000

Data Index: 290945 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.3553. Min Act: -0.0000

Data Index: 447948 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.5955. Min Act: -0.0000

Data Index: 170502 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.4799. Min Act: -0.0000

Data Index: 250094 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.3987. Min Act: -0.0000

Data Index: 499041 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.6196. Min Act: -0.0000

Data Index: 980159 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.4561. Min Act: -0.0000

Data Index: 719498 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.4406. Min Act: -0.0000

Data Index: 558360 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.4267. Min Act: -0.0000

Data Index: 58157 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1005160 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.3131. Min Act: -0.0000

Data Index: 462956 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.3856. Min Act: -0.0000

Data Index: 83906 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 2.6008. Min Range: -2.6008

Max Act: 1.2646. Min Act: -0.0000

Data Index: 620843 (C4 (Web Text))

Max Activating Token Index: 554