Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 29.3318. Min Range: -29.3318
Max Act: 29.2068. Min Act: -0.1700
Data Index: 3193003 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 29.3318. Min Range: -29.3318
Max Act: 29.3318. Min Act: -0.1700
Data Index: 48227 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 29.3318. Min Range: -29.3318
Max Act: 29.0818. Min Act: -0.1700
Data Index: 3868848 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.9568. Min Act: -0.1700
Data Index: 2390570 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.8318. Min Act: -0.1700
Data Index: 6540442 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.5818. Min Act: -0.1700
Data Index: 4695817 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.5818. Min Act: -0.1700
Data Index: 3204383 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.5818. Min Act: -0.1700
Data Index: 2929026 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.5818. Min Act: -0.1700
Data Index: 271756 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.5818. Min Act: -0.1700
Data Index: 2530067 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.4568. Min Act: -0.1700
Data Index: 1440662 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.4568. Min Act: -0.1700
Data Index: 5508044 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.4568. Min Act: -0.1700
Data Index: 4708593 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.4568. Min Act: -0.1700
Data Index: 4127105 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.4568. Min Act: -0.1700
Data Index: 4020851 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.3318. Min Act: -0.1700
Data Index: 6144298 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.3318. Min Act: -0.1700
Data Index: 5767114 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.3318. Min Act: -0.1700
Data Index: 2565398 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.3318. Min Act: -0.1700
Data Index: 5431149 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 29.3318. Min Range: -29.3318
Max Act: 28.3318. Min Act: -0.1700
Data Index: 5134161 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19