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

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

Neuron 1468 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: 4.9304. Min Range: -4.9304

Max Act: 4.9304. Min Act: -0.1442

Data Index: 492209 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.7918. Min Act: -0.1442

Data Index: 1201698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.7735. Min Act: -0.1442

Data Index: 327032 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.7104. Min Act: -0.1700

Data Index: 37369 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6654. Min Act: -0.1675

Data Index: 1460535 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6657. Min Act: -0.1656

Data Index: 1556386 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6701. Min Act: -0.1686

Data Index: 995637 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6669. Min Act: -0.1442

Data Index: 598753 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6382. Min Act: -0.1698

Data Index: 190019 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6505. Min Act: -0.1698

Data Index: 1399733 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6561. Min Act: -0.1699

Data Index: 1654102 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6420. Min Act: -0.1690

Data Index: 38593 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6393. Min Act: -0.1690

Data Index: 527941 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6237. Min Act: -0.1679

Data Index: 883375 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6150. Min Act: -0.1700

Data Index: 664484 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.5964. Min Act: -0.1700

Data Index: 819317 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6242. Min Act: -0.1699

Data Index: 1483220 (Python Code)

Max Activating Token Index: 516

Text #17

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6062. Min Act: -0.1442

Data Index: 485878 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.6266. Min Act: -0.1692

Data Index: 103624 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 4.9304. Min Range: -4.9304

Max Act: 4.5914. Min Act: -0.1700

Data Index: 1435395 (Python Code)

Max Activating Token Index: 1023