Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4716 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.8582. Min Act: -0.1700
Data Index: 7432271 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.7644. Min Act: -0.1700
Data Index: 2764195 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.6707. Min Act: -0.1700
Data Index: 6420795 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.6394. Min Act: -0.1700
Data Index: 8424200 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.5769. Min Act: -0.1700
Data Index: 8424201 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.5769. Min Act: -0.1700
Data Index: 4898370 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.5457. Min Act: -0.1700
Data Index: 6920063 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4832. Min Act: -0.1700
Data Index: 7722603 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4832. Min Act: -0.1700
Data Index: 8736805 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4832. Min Act: -0.1700
Data Index: 8736807 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4207. Min Act: -0.1700
Data Index: 7236588 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4207. Min Act: -0.1700
Data Index: 6173761 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.4207. Min Act: -0.1700
Data Index: 7647015 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3894. Min Act: -0.1700
Data Index: 382866 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3894. Min Act: -0.1700
Data Index: 5373848 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3894. Min Act: -0.1700
Data Index: 1621581 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3582. Min Act: -0.1700
Data Index: 5373847 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3582. Min Act: -0.1700
Data Index: 2189500 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3269. Min Act: -0.1700
Data Index: 7058475 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8582. Min Range: -6.8582
Max Act: 6.3269. Min Act: -0.1700
Data Index: 7687054 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19