Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 7612887 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.8510. Min Act: -0.1700
Data Index: 5141393 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.7885. Min Act: -0.1700
Data Index: 7216373 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6635. Min Act: -0.1700
Data Index: 8197873 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6635. Min Act: -0.1700
Data Index: 1535768 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6010. Min Act: -0.1700
Data Index: 540222 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6010. Min Act: -0.1700
Data Index: 1467168 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6010. Min Act: -0.1700
Data Index: 3899287 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.6010. Min Act: -0.1700
Data Index: 6994306 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.5385. Min Act: -0.1700
Data Index: 4063572 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.5385. Min Act: -0.1700
Data Index: 5340435 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.4760. Min Act: -0.1700
Data Index: 7183058 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.4760. Min Act: -0.1700
Data Index: 6459880 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.4135. Min Act: -0.1700
Data Index: 7006447 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.3510. Min Act: -0.1700
Data Index: 3696578 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.2885. Min Act: -0.1700
Data Index: 1732528 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.3510. Min Act: -0.1700
Data Index: 2477571 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.2885. Min Act: -0.1700
Data Index: 6187286 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.2885. Min Act: -0.1700
Data Index: 6345095 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8510. Min Range: -8.8510
Max Act: 8.2885. Min Act: -0.1700
Data Index: 6906575 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19