Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.8812. Min Act: -0.1700
Data Index: 7973470 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7539654 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.5999. Min Act: -0.1700
Data Index: 605456 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.5687. Min Act: -0.1700
Data Index: 8093539 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.5374. Min Act: -0.1700
Data Index: 1338613 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.5062. Min Act: -0.1700
Data Index: 509557 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4749. Min Act: -0.1700
Data Index: 545310 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4749. Min Act: -0.1700
Data Index: 4423827 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8817203 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4437. Min Act: -0.1700
Data Index: 4990135 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8249674 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4124. Min Act: -0.1700
Data Index: 3536208 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4124. Min Act: -0.1700
Data Index: 8002882 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4124. Min Act: -0.1700
Data Index: 3324110 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4124. Min Act: -0.1700
Data Index: 490226 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.3812. Min Act: -0.1700
Data Index: 1697956 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.4124. Min Act: -0.1700
Data Index: 902307 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.3499. Min Act: -0.1700
Data Index: 3465378 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.3499. Min Act: -0.1700
Data Index: 3123148 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8812. Min Range: -5.8812
Max Act: 5.3499. Min Act: -0.1700
Data Index: 7574926 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19