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

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

Neuron 704 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.3366. Min Act: -0.0000

Data Index: 1379574 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1642917 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1631671 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1412596 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1434752 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1451862 (Python Code)

Max Activating Token Index: 309

Text #6

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1394748 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1650654 (Python Code)

Max Activating Token Index: 788

Text #8

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1430112 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1363541 (Python Code)

Max Activating Token Index: 309

Text #10

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1445009 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1399806 (Python Code)

Max Activating Token Index: 784

Text #12

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1611076 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1527799 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1635533 (Python Code)

Max Activating Token Index: 1012

Text #15

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1428071 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1526105 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 1.3366. Min Range: -1.3366

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1630975 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1605660 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 1.3366. Min Range: -1.3366

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1433699 (Python Code)

Max Activating Token Index: 385