Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 122 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0829. Min Act: -0.1700

Data Index: 1531889 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0940. Min Act: -0.1700

Data Index: 1527540 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0463. Min Act: -0.1700

Data Index: 1623261 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0770. Min Act: -0.1700

Data Index: 1615952 (Python Code)

Max Activating Token Index: 708

Text #4

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0218. Min Act: -0.1700

Data Index: 1542403 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0255. Min Act: -0.1700

Data Index: 1385669 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 4.0940. Min Range: -4.0940

Max Act: 4.0208. Min Act: -0.1700

Data Index: 1376805 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9948. Min Act: -0.1700

Data Index: 1416361 (Python Code)

Max Activating Token Index: 720

Text #8

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9733. Min Act: -0.1700

Data Index: 1557291 (Python Code)

Max Activating Token Index: 472

Text #9

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9762. Min Act: -0.1700

Data Index: 1460601 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9686. Min Act: -0.1700

Data Index: 1462436 (Python Code)

Max Activating Token Index: 100

Text #11

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9517. Min Act: -0.1700

Data Index: 1561839 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9636. Min Act: -0.1700

Data Index: 1487274 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9331. Min Act: -0.1700

Data Index: 1591884 (Python Code)

Max Activating Token Index: 831

Text #14

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9497. Min Act: -0.1700

Data Index: 1473508 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9527. Min Act: -0.1700

Data Index: 1550899 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9356. Min Act: -0.1700

Data Index: 1390211 (Python Code)

Max Activating Token Index: 851

Text #17

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9510. Min Act: -0.1700

Data Index: 1458705 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9448. Min Act: -0.1700

Data Index: 1483234 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 4.0940. Min Range: -4.0940

Max Act: 3.9087. Min Act: -0.1700

Data Index: 1404279 (Python Code)

Max Activating Token Index: 341