Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.8901. Min Act: -0.1700
Data Index: 150674 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.9526. Min Act: -0.1700
Data Index: 8665765 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.8589. Min Act: -0.1700
Data Index: 1736820 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.8901. Min Act: -0.1700
Data Index: 6425554 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.8276. Min Act: -0.1700
Data Index: 1561622 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.8276. Min Act: -0.1700
Data Index: 6675922 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.7651. Min Act: -0.1700
Data Index: 1630134 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5234959 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.7339. Min Act: -0.1700
Data Index: 5249370 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.7339. Min Act: -0.1700
Data Index: 1077440 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6714. Min Act: -0.1700
Data Index: 157502 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6714. Min Act: -0.1700
Data Index: 4754468 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6714. Min Act: -0.1700
Data Index: 5690044 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6714. Min Act: -0.1700
Data Index: 4481341 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6401. Min Act: -0.1700
Data Index: 4600896 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6401. Min Act: -0.1700
Data Index: 5681151 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6401. Min Act: -0.1700
Data Index: 3211409 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6714. Min Act: -0.1700
Data Index: 1059903 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6089. Min Act: -0.1700
Data Index: 5690045 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9526. Min Range: -4.9526
Max Act: 4.6089. Min Act: -0.1700
Data Index: 2909943 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19