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

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

Neuron 732 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: 4.9398. Min Range: -4.9398

Max Act: 4.9398. Min Act: -0.1700

Data Index: 383572 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.8000. Min Act: -0.1700

Data Index: 374112 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.7390. Min Act: -0.1700

Data Index: 1520652 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.7696. Min Act: -0.1700

Data Index: 861748 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.7493. Min Act: -0.1700

Data Index: 1557135 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6965. Min Act: -0.1700

Data Index: 904088 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6816. Min Act: -0.1700

Data Index: 405690 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6713. Min Act: -0.1700

Data Index: 1207661 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6251. Min Act: -0.1700

Data Index: 819383 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6415. Min Act: -0.1700

Data Index: 178988 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6638. Min Act: -0.1700

Data Index: 1424686 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6363. Min Act: -0.1700

Data Index: 1250146 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6016. Min Act: -0.1700

Data Index: 40941 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.6181. Min Act: -0.1700

Data Index: 1153153 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5809. Min Act: -0.1700

Data Index: 1238032 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5883. Min Act: -0.1700

Data Index: 22115 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5972. Min Act: -0.1700

Data Index: 975273 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5819. Min Act: -0.1700

Data Index: 1606983 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5649. Min Act: -0.1700

Data Index: 1369594 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 4.9398. Min Range: -4.9398

Max Act: 4.5686. Min Act: -0.1700

Data Index: 1044549 (C4 (Web Text))

Max Activating Token Index: 13