Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4305 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.9182. Min Act: -0.1700
Data Index: 6594916 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7774. Min Act: -0.1700
Data Index: 6954360 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.7149. Min Act: -0.1700
Data Index: 144368 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6992. Min Act: -0.1700
Data Index: 1978692 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6679. Min Act: -0.1700
Data Index: 4913047 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6836. Min Act: -0.1700
Data Index: 1978691 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6523. Min Act: -0.1700
Data Index: 5577680 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6367. Min Act: -0.1700
Data Index: 2219857 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6523. Min Act: -0.1700
Data Index: 8758887 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6054. Min Act: -0.1700
Data Index: 5806161 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6054. Min Act: -0.1700
Data Index: 4166684 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6210. Min Act: -0.1700
Data Index: 5768693 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.6054. Min Act: -0.1700
Data Index: 5768695 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5584. Min Act: -0.1700
Data Index: 1050038 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5584. Min Act: -0.1700
Data Index: 5071624 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5584. Min Act: -0.1700
Data Index: 7244861 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5584. Min Act: -0.1700
Data Index: 3128872 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5427. Min Act: -0.1700
Data Index: 432453 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.5114. Min Act: -0.1700
Data Index: 5659218 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9182. Min Range: -3.9182
Max Act: 3.4958. Min Act: -0.1700
Data Index: 5567848 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19