Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.9438. Min Act: -0.1700
Data Index: 3747470 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.9750. Min Act: -0.1700
Data Index: 906685 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8813. Min Act: -0.1700
Data Index: 2544529 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8813. Min Act: -0.1700
Data Index: 2537176 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8500. Min Act: -0.1700
Data Index: 4549852 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8188. Min Act: -0.1700
Data Index: 6298999 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.8188. Min Act: -0.1700
Data Index: 2433702 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 8303225 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 1009352 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 921457 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 685330 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 5255930 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 3277919 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 1301724 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 3347775 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 219861 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 4355267 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 1004341 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 8391703 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9750. Min Range: -4.9750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 4188630 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19