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

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

Neuron 3060 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: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1514436 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1066477 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1575625 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4644. Min Act: -0.0001

Data Index: 1635144 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1478333 (Python Code)

Max Activating Token Index: 396

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1509258 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1533243 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1527266 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1557179 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1445058 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4281. Min Act: -0.0000

Data Index: 652355 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1591778 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1555827 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1459786 (Python Code)

Max Activating Token Index: 113

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1565134 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1429779 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1547991 (Python Code)

Max Activating Token Index: 986

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1551840 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1428199 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1509226 (Python Code)

Max Activating Token Index: 957