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

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

Neuron 1378 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.5889. Min Act: -0.0001

Data Index: 1385272 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.7422. Min Act: -0.0000

Data Index: 1639120 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1459494 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1641111 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1627799 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1433042 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1370329 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1442812 (Python Code)

Max Activating Token Index: 601

Text #8

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1460705 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3032. Min Act: -0.0001

Data Index: 1465114 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3358. Min Act: -0.0001

Data Index: 1495267 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1471717 (Python Code)

Max Activating Token Index: 800

Text #12

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1374931 (Python Code)

Max Activating Token Index: 434

Text #13

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1606092 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1493169 (Python Code)

Max Activating Token Index: 515

Text #15

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2952. Min Act: -0.0000

Data Index: 1481155 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.1734. Min Act: -0.0001

Data Index: 1394544 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1632660 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.3277. Min Act: -0.0000

Data Index: 1428424 (Python Code)

Max Activating Token Index: 589

Text #19

Max Range: 1.7422. Min Range: -1.7422

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1506598 (Python Code)

Max Activating Token Index: 870