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

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

Neuron 5527 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.5807. Min Act: -0.0000

Data Index: 1200640 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1541485 (Python Code)

Max Activating Token Index: 261

Text #2

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.5551. Min Act: -0.0000

Data Index: 531266 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.4384. Min Act: -0.0000

Data Index: 572470 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.4907. Min Act: -0.0000

Data Index: 245722 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.4614. Min Act: -0.0000

Data Index: 792603 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1473473 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1542431 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3973. Min Act: -0.0000

Data Index: 588906 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1367801 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3150. Min Act: -0.0000

Data Index: 594611 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1384366 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1012454 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3334. Min Act: -0.0000

Data Index: 475125 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.2616. Min Act: -0.0000

Data Index: 566948 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1248282 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3250. Min Act: -0.0000

Data Index: 540206 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3215. Min Act: -0.0000

Data Index: 495630 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3066. Min Act: -0.0000

Data Index: 97313 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.5807. Min Range: -1.5807

Max Act: 1.3101. Min Act: -0.0000

Data Index: 523322 (C4 (Web Text))

Max Activating Token Index: 978