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

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

Neuron 334 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0002

Data Index: 293806 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1599292 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1624366 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0468. Min Act: -0.0002

Data Index: 836698 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1596250 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1499313 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0466. Min Act: -0.0002

Data Index: 293257 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0465. Min Act: -0.0002

Data Index: 452639 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1336613 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1628345 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1568604 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0456. Min Act: -0.0002

Data Index: 878619 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0456. Min Act: -0.0002

Data Index: 597812 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1144739 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1297627 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1341500 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1363770 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0450. Min Act: -0.0002

Data Index: 695113 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0449. Min Act: -0.0002

Data Index: 54726 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0450. Min Act: -0.0002

Data Index: 104751 (C4 (Web Text))

Max Activating Token Index: 104