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

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

Neuron 1477 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: 4.6765. Min Range: -4.6765

Max Act: 4.6765. Min Act: -0.1700

Data Index: 1543389 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6268. Min Act: -0.1700

Data Index: 1654378 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6478. Min Act: -0.1700

Data Index: 1408852 (Python Code)

Max Activating Token Index: 197

Text #3

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6429. Min Act: -0.1700

Data Index: 1594854 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6383. Min Act: -0.1700

Data Index: 1604218 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6067. Min Act: -0.1700

Data Index: 1539044 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5890. Min Act: -0.1700

Data Index: 1606196 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.6284. Min Act: -0.1700

Data Index: 1626511 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5979. Min Act: -0.1700

Data Index: 1652594 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5700. Min Act: -0.1700

Data Index: 1504318 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5790. Min Act: -0.1700

Data Index: 1651694 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5751. Min Act: -0.1700

Data Index: 1649463 (Python Code)

Max Activating Token Index: 464

Text #12

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5965. Min Act: -0.1700

Data Index: 1451017 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5856. Min Act: -0.1700

Data Index: 1450436 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5854. Min Act: -0.1700

Data Index: 1437957 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5613. Min Act: -0.1700

Data Index: 1436763 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5853. Min Act: -0.1700

Data Index: 1504544 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5758. Min Act: -0.1700

Data Index: 1413482 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5758. Min Act: -0.1700

Data Index: 1495895 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 4.6765. Min Range: -4.6765

Max Act: 4.5337. Min Act: -0.1700

Data Index: 1455534 (Python Code)

Max Activating Token Index: 503