Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4898. Min Range: -8.4898
Max Act: 8.4898. Min Act: -0.1700
Data Index: 95301 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4898. Min Range: -8.4898
Max Act: 8.0523. Min Act: -0.1700
Data Index: 2895688 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.9586. Min Act: -0.1700
Data Index: 3664002 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.9273. Min Act: -0.1700
Data Index: 645771 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.8336. Min Act: -0.1700
Data Index: 4783642 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.7711. Min Act: -0.1700
Data Index: 3332307 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.8023. Min Act: -0.1700
Data Index: 346422 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.7086. Min Act: -0.1700
Data Index: 8331821 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.6461. Min Act: -0.1700
Data Index: 7269891 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.6461. Min Act: -0.1700
Data Index: 1322956 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.6461. Min Act: -0.1700
Data Index: 7728224 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.6148. Min Act: -0.1700
Data Index: 296181 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.6148. Min Act: -0.1700
Data Index: 5702058 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5836. Min Act: -0.1700
Data Index: 1487515 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5523. Min Act: -0.1700
Data Index: 7042766 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5523. Min Act: -0.1700
Data Index: 6341237 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5523. Min Act: -0.1700
Data Index: 2331314 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5523. Min Act: -0.1700
Data Index: 4337853 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.5211. Min Act: -0.1700
Data Index: 546787 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4898. Min Range: -8.4898
Max Act: 7.4898. Min Act: -0.1700
Data Index: 829384 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19