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

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

Neuron 5863 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: 0.3197. Min Range: -0.3197

Max Act: 0.3155. Min Act: -0.0000

Data Index: 515890 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3197. Min Act: -0.0000

Data Index: 436408 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2784. Min Act: -0.0000

Data Index: 118725 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2850. Min Act: -0.0000

Data Index: 517898 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2673. Min Act: -0.0000

Data Index: 62378 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2596. Min Act: -0.0000

Data Index: 421813 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2540. Min Act: -0.0000

Data Index: 596768 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1124571 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2535. Min Act: -0.0000

Data Index: 137552 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1110638 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2521. Min Act: -0.0000

Data Index: 853786 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1214448 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2475. Min Act: -0.0000

Data Index: 482514 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2448. Min Act: -0.0000

Data Index: 253256 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2308. Min Act: -0.0000

Data Index: 904974 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2563. Min Act: -0.0000

Data Index: 432275 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2376. Min Act: -0.0000

Data Index: 328339 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2348. Min Act: -0.0000

Data Index: 86052 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2413. Min Act: -0.0000

Data Index: 45181 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1265851 (C4 (Web Text))

Max Activating Token Index: 938