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

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

Neuron 934 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: 2.9928. Min Range: -2.9928

Max Act: 2.9928. Min Act: -0.1700

Data Index: 1393771 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8874. Min Act: -0.1700

Data Index: 1589222 (Python Code)

Max Activating Token Index: 846

Text #2

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8534. Min Act: -0.1700

Data Index: 1346456 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8560. Min Act: -0.1700

Data Index: 256098 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8449. Min Act: -0.1700

Data Index: 1528406 (Python Code)

Max Activating Token Index: 638

Text #5

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8355. Min Act: -0.1700

Data Index: 1133332 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8387. Min Act: -0.1700

Data Index: 1420174 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8400. Min Act: -0.1700

Data Index: 1473522 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8468. Min Act: -0.1700

Data Index: 199910 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8181. Min Act: -0.1700

Data Index: 1166369 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8295. Min Act: -0.1700

Data Index: 530369 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7943. Min Act: -0.1700

Data Index: 1424979 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8040. Min Act: -0.1700

Data Index: 1413040 (Python Code)

Max Activating Token Index: 439

Text #13

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8021. Min Act: -0.1700

Data Index: 570918 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7980. Min Act: -0.1700

Data Index: 1490319 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7959. Min Act: -0.1700

Data Index: 695805 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7970. Min Act: -0.1700

Data Index: 964606 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7752. Min Act: -0.1700

Data Index: 1638852 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.7739. Min Act: -0.1700

Data Index: 1650868 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 2.9928. Min Range: -2.9928

Max Act: 2.8052. Min Act: -0.1700

Data Index: 1483957 (Python Code)

Max Activating Token Index: 837