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

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

Neuron 1940 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: 3.8300. Min Range: -3.8300

Max Act: 3.8300. Min Act: -0.1700

Data Index: 1557015 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.7074. Min Act: -0.1700

Data Index: 1536457 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1601555 (Python Code)

Max Activating Token Index: 423

Text #3

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1549010 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6695. Min Act: -0.1700

Data Index: 1375729 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6462. Min Act: -0.1700

Data Index: 1485602 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6465. Min Act: -0.1700

Data Index: 1541016 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1548845 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6087. Min Act: -0.1700

Data Index: 1614885 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1415973 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.6046. Min Act: -0.1700

Data Index: 1568499 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5832. Min Act: -0.1700

Data Index: 1393462 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1611445 (Python Code)

Max Activating Token Index: 203

Text #13

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5590. Min Act: -0.1700

Data Index: 1373019 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5295. Min Act: -0.1700

Data Index: 1386142 (Python Code)

Max Activating Token Index: 636

Text #15

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1594864 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1533024 (Python Code)

Max Activating Token Index: 5

Text #17

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5525. Min Act: -0.1700

Data Index: 1538501 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1552191 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 3.8300. Min Range: -3.8300

Max Act: 3.5345. Min Act: -0.1700

Data Index: 1591997 (Python Code)

Max Activating Token Index: 1023