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

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

Neuron 839 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: 13.5272. Min Range: -13.5272

Max Act: 13.5272. Min Act: -0.1700

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.2734. Min Act: -0.1700

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.1525. Min Act: -0.1700

Data Index: 1436275 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.1466. Min Act: -0.1700

Data Index: 1520583 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.1120. Min Act: -0.1700

Data Index: 1566267 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.0206. Min Act: -0.1700

Data Index: 1404851 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 13.5272. Min Range: -13.5272

Max Act: 13.0653. Min Act: -0.1700

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.8579. Min Act: -0.1700

Data Index: 1629689 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.8691. Min Act: -0.1700

Data Index: 1592952 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.9124. Min Act: -0.1700

Data Index: 1007764 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.8487. Min Act: -0.1700

Data Index: 808309 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.8558. Min Act: -0.1700

Data Index: 1471702 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.8679. Min Act: -0.1700

Data Index: 1548149 (Python Code)

Max Activating Token Index: 537

Text #13

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.7373. Min Act: -0.1700

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.7062. Min Act: -0.1700

Data Index: 1518118 (Python Code)

Max Activating Token Index: 553

Text #15

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.7510. Min Act: -0.1700

Data Index: 1541679 (Python Code)

Max Activating Token Index: 483

Text #16

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.7117. Min Act: -0.1700

Data Index: 1551139 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.6576. Min Act: -0.1700

Data Index: 1609647 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.6590. Min Act: -0.1700

Data Index: 1363578 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 13.5272. Min Range: -13.5272

Max Act: 12.5945. Min Act: -0.1700

Data Index: 1602194 (Python Code)

Max Activating Token Index: 174