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

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

Neuron 746 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: 4.3249. Min Range: -4.3249

Max Act: 4.3249. Min Act: -0.1699

Data Index: 804802 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.3200. Min Act: -0.1699

Data Index: 1542544 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.3025. Min Act: -0.1700

Data Index: 1461495 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2907. Min Act: -0.1700

Data Index: 1275597 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2891. Min Act: -0.1699

Data Index: 7821 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2575. Min Act: -0.1700

Data Index: 1518564 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2054. Min Act: -0.1698

Data Index: 224219 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2269. Min Act: -0.1696

Data Index: 1544739 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2271. Min Act: -0.1699

Data Index: 1388671 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.2223. Min Act: -0.1700

Data Index: 279482 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1822. Min Act: -0.1698

Data Index: 742084 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1764. Min Act: -0.1140

Data Index: 1405002 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1790. Min Act: -0.1662

Data Index: 56845 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1543. Min Act: -0.1699

Data Index: 767030 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1473. Min Act: -0.1699

Data Index: 1506553 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1678. Min Act: -0.1693

Data Index: 807845 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1527. Min Act: -0.1698

Data Index: 605356 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1429. Min Act: -0.1699

Data Index: 604531 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1502. Min Act: -0.1700

Data Index: 66464 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 4.3249. Min Range: -4.3249

Max Act: 4.1596. Min Act: -0.1700

Data Index: 1252563 (C4 (Web Text))

Max Activating Token Index: 937