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

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

Neuron 1433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8493. Min Act: -0.0000

Data Index: 942008 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8784. Min Act: -0.0000

Data Index: 947414 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8504. Min Act: -0.0000

Data Index: 612109 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1433568 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1215161 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7905. Min Act: -0.0000

Data Index: 962990 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7521. Min Act: -0.0000

Data Index: 147542 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1227892 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7680. Min Act: -0.0000

Data Index: 277874 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7503. Min Act: -0.0000

Data Index: 540738 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7369. Min Act: -0.0000

Data Index: 750824 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7526. Min Act: -0.0000

Data Index: 114528 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7437. Min Act: -0.0000

Data Index: 717835 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1025680 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7593. Min Act: -0.0000

Data Index: 898318 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7624. Min Act: -0.0000

Data Index: 885686 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7330. Min Act: -0.0000

Data Index: 734553 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1140346 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7278. Min Act: -0.0000

Data Index: 449096 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1174904 (C4 (Web Text))

Max Activating Token Index: 762