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

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

Neuron 4695 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.4850. Min Act: -0.0000

Data Index: 697451 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.4141. Min Act: -0.0000

Data Index: 890750 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.3585. Min Act: -0.0000

Data Index: 657531 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1223281 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.2051. Min Act: -0.0000

Data Index: 394548 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.1664. Min Act: -0.0000

Data Index: 1337040 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.1376. Min Act: -0.0000

Data Index: 1094170 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.1064. Min Act: -0.0000

Data Index: 912912 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.2017. Min Act: -0.0000

Data Index: 554652 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0897. Min Act: -0.0000

Data Index: 703602 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1186785 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0130. Min Act: 0.0000

Data Index: 646246 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0149. Min Act: 0.0000

Data Index: 1056266 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 2.4850. Min Range: -2.4850

Max Act: 1.8896. Min Act: -0.0000

Data Index: 1099385 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0637. Min Act: -0.0000

Data Index: 1283665 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 2.4850. Min Range: -2.4850

Max Act: 1.9555. Min Act: -0.0000

Data Index: 623883 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 2.4850. Min Range: -2.4850

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1090304 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.4850. Min Range: -2.4850

Max Act: 1.9279. Min Act: -0.0000

Data Index: 1246805 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 2.4850. Min Range: -2.4850

Max Act: 2.0340. Min Act: -0.0000

Data Index: 769521 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 2.4850. Min Range: -2.4850

Max Act: 1.8981. Min Act: -0.0000

Data Index: 865068 (C4 (Web Text))

Max Activating Token Index: 333