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

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

Neuron 3639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.3083. Min Act: -0.0000

Data Index: 375932 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0459. Min Act: -0.0000

Data Index: 873534 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1178018 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.8676. Min Act: -0.0000

Data Index: 337977 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.6417. Min Act: -0.0000

Data Index: 1242365 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.6378. Min Act: -0.0000

Data Index: 1199486 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1007621 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.5667. Min Act: -0.0000

Data Index: 205897 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.6240. Min Act: -0.0000

Data Index: 138201 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.7361. Min Act: -0.0000

Data Index: 902589 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.5677. Min Act: -0.0000

Data Index: 333347 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.7870. Min Act: -0.0000

Data Index: 650342 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.5017. Min Act: -0.0000

Data Index: 556552 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.3895. Min Act: -0.0000

Data Index: 130263 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.3519. Min Act: -0.0000

Data Index: 611557 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.3062. Min Act: -0.0000

Data Index: 1081216 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.2089. Min Act: -0.0000

Data Index: 346389 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.1722. Min Act: -0.0000

Data Index: 318156 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.1985. Min Act: -0.0000

Data Index: 1346907 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 3.3083. Min Range: -3.3083

Max Act: 2.1807. Min Act: -0.0000

Data Index: 746314 (C4 (Web Text))

Max Activating Token Index: 183