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

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

Neuron 1280 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: 3.1479. Min Range: -3.1479

Max Act: 3.1479. Min Act: -0.1700

Data Index: 1608643 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 3.1479. Min Range: -3.1479

Max Act: 3.1124. Min Act: -0.1700

Data Index: 1597598 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 3.1479. Min Range: -3.1479

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1650416 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 3.1479. Min Range: -3.1479

Max Act: 3.0639. Min Act: -0.1700

Data Index: 1648631 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 3.1479. Min Range: -3.1479

Max Act: 3.0506. Min Act: -0.1700

Data Index: 1376324 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9967. Min Act: -0.1700

Data Index: 1384718 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9684. Min Act: -0.1700

Data Index: 1422522 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9778. Min Act: -0.1700

Data Index: 1412553 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9539. Min Act: -0.1700

Data Index: 1581180 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9601. Min Act: -0.1700

Data Index: 1488443 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9277. Min Act: -0.1700

Data Index: 1539190 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9419. Min Act: -0.1700

Data Index: 1470856 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9207. Min Act: -0.1700

Data Index: 1534322 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9065. Min Act: -0.1700

Data Index: 1551707 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9142. Min Act: -0.1700

Data Index: 1389496 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9147. Min Act: -0.1700

Data Index: 1642264 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.9179. Min Act: -0.1700

Data Index: 1630334 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.8995. Min Act: -0.1700

Data Index: 1634105 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.8980. Min Act: -0.1700

Data Index: 1368226 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 3.1479. Min Range: -3.1479

Max Act: 2.8962. Min Act: -0.1700

Data Index: 1501677 (Python Code)

Max Activating Token Index: 7