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

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

Neuron 787 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1535353 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1554227 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3882. Min Act: -0.0000

Data Index: 1509003 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1633303 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1526397 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1570149 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1495418 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1390862 (Python Code)

Max Activating Token Index: 863

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1441797 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1554470 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1555204 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1587986 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1513581 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1637753 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1475240 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1393905 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1495197 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1452249 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1458254 (Python Code)

Max Activating Token Index: 586

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1549652 (Python Code)

Max Activating Token Index: 734