Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1030 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7805. Min Act: -0.0000

Data Index: 741929 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.7534. Min Act: -0.0000

Data Index: 940254 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6196. Min Act: -0.0000

Data Index: 402061 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1060750 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1297817 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1209708 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1159616 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3221. Min Act: -0.0000

Data Index: 401312 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3496. Min Act: -0.0000

Data Index: 715467 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3164. Min Act: -0.0000

Data Index: 387651 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3298. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1054266 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.3160. Min Act: -0.0000

Data Index: 29650 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2787. Min Act: -0.0000

Data Index: 743573 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2825. Min Act: -0.0000

Data Index: 736616 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2720. Min Act: -0.0000

Data Index: 608612 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1305940 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1499199 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2684. Min Act: -0.0001

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7805. Min Range: -0.7805

Max Act: 0.2623. Min Act: -0.0000

Data Index: 906310 (C4 (Web Text))

Max Activating Token Index: 516