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

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

Neuron 5700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0324. Min Range: -3.0324

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1122010 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.1631. Min Act: -0.0000

Data Index: 1629772 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.0275. Min Act: -0.0000

Data Index: 1436039 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.1417. Min Act: -0.0000

Data Index: 1639689 (Python Code)

Max Activating Token Index: 459

Text #4

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.0511. Min Act: -0.0000

Data Index: 1639478 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.1399. Min Act: -0.0000

Data Index: 102083 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.1448. Min Act: -0.0000

Data Index: 1534434 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9951. Min Act: -0.0000

Data Index: 1412599 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.0016. Min Act: -0.0000

Data Index: 1420807 (Python Code)

Max Activating Token Index: 321

Text #9

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.0012. Min Act: -0.0000

Data Index: 1433442 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.8782. Min Act: -0.0000

Data Index: 1244921 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9658. Min Act: -0.0000

Data Index: 1598245 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1050228 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9294. Min Act: -0.0000

Data Index: 1481587 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9270. Min Act: -0.0000

Data Index: 1635203 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.8981. Min Act: -0.0000

Data Index: 1480769 (Python Code)

Max Activating Token Index: 445

Text #16

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1649112 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.9700. Min Act: -0.0000

Data Index: 906459 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.7448. Min Act: -0.0000

Data Index: 1370107 (Python Code)

Max Activating Token Index: 494

Text #19

Max Range: 3.0324. Min Range: -3.0324

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1413435 (Python Code)

Max Activating Token Index: 17