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

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

Neuron 5700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8007. Min Range: -3.8007

Max Act: 3.8007. Min Act: -0.0000

Data Index: 583410 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 3.8007. Min Range: -3.8007

Max Act: 3.5455. Min Act: -0.0000

Data Index: 1016125 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.5839. Min Act: -0.0000

Data Index: 844553 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.8445. Min Act: -0.0000

Data Index: 744396 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.4563. Min Act: -0.0000

Data Index: 1113483 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.5815. Min Act: -0.0000

Data Index: 25275 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.5418. Min Act: -0.0000

Data Index: 297480 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.7292. Min Act: -0.0000

Data Index: 309705 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.3421. Min Act: -0.0000

Data Index: 1564376 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.6999. Min Act: -0.0000

Data Index: 1190948 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.1828. Min Act: -0.0000

Data Index: 331860 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.3804. Min Act: -0.0000

Data Index: 121067 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.0521. Min Act: -0.0000

Data Index: 350941 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.7735. Min Act: -0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.1029. Min Act: -0.0000

Data Index: 231766 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.0716. Min Act: -0.0000

Data Index: 930391 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.0504. Min Act: -0.0000

Data Index: 737327 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.2532. Min Act: -0.0000

Data Index: 1112883 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.2837. Min Act: -0.0000

Data Index: 1444554 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 3.8007. Min Range: -3.8007

Max Act: 2.2112. Min Act: -0.0000

Data Index: 491419 (C4 (Web Text))

Max Activating Token Index: 845