Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0390. Min Act: -0.0003

Data Index: 243919 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0345. Min Act: -0.0003

Data Index: 787653 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0362. Min Act: -0.0003

Data Index: 147614 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1357912 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0320. Min Act: -0.0003

Data Index: 142033 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1262404 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1392104 (Python Code)

Max Activating Token Index: 692

Text #7

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1644944 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1132478 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0316. Min Act: -0.0003

Data Index: 663734 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1580348 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1645093 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1648522 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1497570 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1582701 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0319. Min Act: -0.0003

Data Index: 956182 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1501799 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1467478 (Python Code)

Max Activating Token Index: 276

Text #19

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1371261 (Python Code)

Max Activating Token Index: 991