Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3333 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1593801 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1503895 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1514765 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1471617 (Python Code)

Max Activating Token Index: 406

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1613605 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1495196 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1017241 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1445147 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1595416 (Python Code)

Max Activating Token Index: 800

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0597. Min Act: 0.0000

Data Index: 1592393 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1142284 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1415424 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1358077 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1430088 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1824 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1498547 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1336333 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0479. Min Act: 0.0000

Data Index: 1438244 (Python Code)

Max Activating Token Index: 602

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1570791 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0484. Min Act: -0.0000

Data Index: 859399 (C4 (Web Text))

Max Activating Token Index: 419