Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0736. Min Range: -6.0736
Max Act: 6.0736. Min Act: -0.1700
Data Index: 5704812 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0736. Min Range: -6.0736
Max Act: 6.0736. Min Act: -0.1700
Data Index: 5704791 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0736. Min Range: -6.0736
Max Act: 6.0423. Min Act: -0.1700
Data Index: 2746193 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.9798. Min Act: -0.1700
Data Index: 5657906 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.9486. Min Act: -0.1700
Data Index: 5657922 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.8861. Min Act: -0.1700
Data Index: 4926796 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.8861. Min Act: -0.1700
Data Index: 4926819 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.8236. Min Act: -0.1700
Data Index: 4907929 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.5736. Min Act: -0.1700
Data Index: 8544751 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 3165492 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.5423. Min Act: -0.1700
Data Index: 3165508 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 4272103 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 4124316 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 5068472 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 8235282 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7063843 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.3861. Min Act: -0.1700
Data Index: 5540102 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.3861. Min Act: -0.1700
Data Index: 470550 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.3548. Min Act: -0.1700
Data Index: 3504948 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0736. Min Range: -6.0736
Max Act: 5.3236. Min Act: -0.1700
Data Index: 1543708 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19