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

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

Neuron 3851 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.6747. Min Act: -0.0000

Data Index: 1399356 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1578382 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1584703 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.3783. Min Act: -0.0000

Data Index: 245212 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1508268 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.3800. Min Act: -0.0000

Data Index: 1616912 (Python Code)

Max Activating Token Index: 1010

Text #6

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1239619 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2632. Min Act: -0.0000

Data Index: 13352 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1154865 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2236. Min Act: -0.0000

Data Index: 1582570 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2259. Min Act: -0.0000

Data Index: 833629 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.3026. Min Act: -0.0000

Data Index: 25361 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.2258. Min Act: -0.0000

Data Index: 127607 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1537681 (Python Code)

Max Activating Token Index: 878

Text #14

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1474886 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1323. Min Act: -0.0000

Data Index: 696876 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1987. Min Act: -0.0000

Data Index: 871382 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1433545 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1363943 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 1.7699. Min Range: -1.7699

Max Act: 1.1393. Min Act: -0.0000

Data Index: 404333 (C4 (Web Text))

Max Activating Token Index: 47