Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0522. Min Act: -0.0004

Data Index: 465034 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0004

Data Index: 215589 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0497. Min Act: -0.0004

Data Index: 706045 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0530. Min Act: -0.0004

Data Index: 66119 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0519. Min Act: -0.0004

Data Index: 912395 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0457. Min Act: -0.0004

Data Index: 158860 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0472. Min Act: -0.0004

Data Index: 1407275 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0452. Min Act: -0.0004

Data Index: 480547 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0417. Min Act: -0.0004

Data Index: 823625 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0470. Min Act: -0.0004

Data Index: 1639097 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1502433 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1573085 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0464. Min Act: -0.0004

Data Index: 1305090 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0469. Min Act: -0.0004

Data Index: 123251 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0476. Min Act: -0.0004

Data Index: 797431 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0436. Min Act: -0.0004

Data Index: 927343 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0470. Min Act: -0.0004

Data Index: 1432179 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0415. Min Act: -0.0004

Data Index: 301597 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0484. Min Act: -0.0004

Data Index: 931144 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0404. Min Act: -0.0004

Data Index: 866819 (C4 (Web Text))

Max Activating Token Index: 145