Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0637. Min Range: -6.0637
Max Act: 6.0637. Min Act: -0.1700
Data Index: 8695362 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.9387. Min Act: -0.1700
Data Index: 4462573 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.8137. Min Act: -0.1700
Data Index: 2377098 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.6887. Min Act: -0.1700
Data Index: 2529225 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.6887. Min Act: -0.1700
Data Index: 7426934 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.5949. Min Act: -0.1700
Data Index: 7953267 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.5637. Min Act: -0.1700
Data Index: 4435550 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4699. Min Act: -0.1700
Data Index: 52970 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4699. Min Act: -0.1700
Data Index: 6715893 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4387. Min Act: -0.1700
Data Index: 4856455 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4387. Min Act: -0.1700
Data Index: 1850683 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4074. Min Act: -0.1700
Data Index: 8419229 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.3762. Min Act: -0.1700
Data Index: 7881772 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4074. Min Act: -0.1700
Data Index: 3408817 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4387. Min Act: -0.1700
Data Index: 5132562 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.4074. Min Act: -0.1700
Data Index: 1336956 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.3762. Min Act: -0.1700
Data Index: 2531824 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.3762. Min Act: -0.1700
Data Index: 8219085 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.3762. Min Act: -0.1700
Data Index: 899560 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0637. Min Range: -6.0637
Max Act: 5.3449. Min Act: -0.1700
Data Index: 3901408 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19