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

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

Neuron 5204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0981. Min Range: -2.0981

Max Act: 2.0981. Min Act: -0.0000

Data Index: 1458469 (Python Code)

Max Activating Token Index: 561

Text #1

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.8034. Min Act: -0.0000

Data Index: 1561972 (Python Code)

Max Activating Token Index: 237

Text #2

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.9489. Min Act: -0.0000

Data Index: 1379150 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.9382. Min Act: -0.0000

Data Index: 1604687 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7983. Min Act: -0.0000

Data Index: 1413691 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.8724. Min Act: -0.0000

Data Index: 1564300 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1462365 (Python Code)

Max Activating Token Index: 376

Text #7

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.8601. Min Act: -0.0000

Data Index: 1500784 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.8546. Min Act: -0.0000

Data Index: 1491629 (Python Code)

Max Activating Token Index: 642

Text #9

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1541620 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1511292 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1500239 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1532050 (Python Code)

Max Activating Token Index: 121

Text #13

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1497847 (Python Code)

Max Activating Token Index: 299

Text #14

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7267. Min Act: -0.0000

Data Index: 1646875 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7797. Min Act: -0.0000

Data Index: 1465327 (Python Code)

Max Activating Token Index: 363

Text #16

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.7701. Min Act: -0.0000

Data Index: 1537958 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1411373 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1505028 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 2.0981. Min Range: -2.0981

Max Act: 1.6307. Min Act: -0.0000

Data Index: 1412064 (Python Code)

Max Activating Token Index: 553