Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2219 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2865. Min Range: -6.2865
Max Act: 6.2865. Min Act: -0.1700
Data Index: 4960764 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2865. Min Range: -6.2865
Max Act: 6.1928. Min Act: -0.1700
Data Index: 3167303 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2865. Min Range: -6.2865
Max Act: 6.0990. Min Act: -0.1700
Data Index: 4180048 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2865. Min Range: -6.2865
Max Act: 6.0990. Min Act: -0.1700
Data Index: 7445510 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2865. Min Range: -6.2865
Max Act: 6.0053. Min Act: -0.1700
Data Index: 5481439 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9740. Min Act: -0.1700
Data Index: 1217171 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9428. Min Act: -0.1700
Data Index: 4960756 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9428. Min Act: -0.1700
Data Index: 1088863 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9428. Min Act: -0.1700
Data Index: 4433387 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9740. Min Act: -0.1700
Data Index: 8237240 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.9115. Min Act: -0.1700
Data Index: 4960754 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8803. Min Act: -0.1700
Data Index: 7685946 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8490. Min Act: -0.1700
Data Index: 5995025 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8178. Min Act: -0.1700
Data Index: 8299991 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8490. Min Act: -0.1700
Data Index: 5124172 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8178. Min Act: -0.1700
Data Index: 544791 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.8178. Min Act: -0.1700
Data Index: 8592198 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.7865. Min Act: -0.1700
Data Index: 5716640 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.7865. Min Act: -0.1700
Data Index: 7210007 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2865. Min Range: -6.2865
Max Act: 5.7865. Min Act: -0.1700
Data Index: 3591847 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19