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

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

Neuron 5428 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: 2.7133. Min Range: -2.7133

Max Act: 2.7133. Min Act: -0.0000

Data Index: 148184 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.5857. Min Act: -0.0000

Data Index: 121221 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.4567. Min Act: -0.0000

Data Index: 589081 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.3151. Min Act: -0.0000

Data Index: 314704 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.0927. Min Act: -0.0000

Data Index: 1562260 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.9984. Min Act: -0.0000

Data Index: 851918 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1528700 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.0690. Min Act: -0.0000

Data Index: 220623 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.8591. Min Act: -0.0000

Data Index: 822746 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.9111. Min Act: -0.0000

Data Index: 1279397 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.9078. Min Act: -0.0000

Data Index: 309181 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1101632 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.6951. Min Act: -0.0000

Data Index: 1032206 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.7851. Min Act: -0.0000

Data Index: 1185063 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.8416. Min Act: -0.0000

Data Index: 1239075 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.7023. Min Act: -0.0000

Data Index: 283049 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 2.7133. Min Range: -2.7133

Max Act: 2.0068. Min Act: -0.0000

Data Index: 1593906 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.6722. Min Act: -0.0000

Data Index: 1655301 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.7637. Min Act: -0.0000

Data Index: 1393734 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 2.7133. Min Range: -2.7133

Max Act: 1.7625. Min Act: -0.0000

Data Index: 408673 (C4 (Web Text))

Max Activating Token Index: 81