Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1074 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7948. Min Act: -0.1700
Data Index: 2773354 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7636. Min Act: -0.1700
Data Index: 48146 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7323. Min Act: -0.1700
Data Index: 771540 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7011. Min Act: -0.1700
Data Index: 8290635 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7011. Min Act: -0.1700
Data Index: 7905798 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7011. Min Act: -0.1700
Data Index: 6216842 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6698. Min Act: -0.1700
Data Index: 3200149 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.7011. Min Act: -0.1700
Data Index: 5498516 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6386. Min Act: -0.1700
Data Index: 6326097 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1970325 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6698. Min Act: -0.1700
Data Index: 2822079 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6386. Min Act: -0.1700
Data Index: 8385388 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6073. Min Act: -0.1700
Data Index: 6576477 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1726301 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6386. Min Act: -0.1700
Data Index: 673841 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6698. Min Act: -0.1700
Data Index: 4620094 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.5761. Min Act: -0.1700
Data Index: 7655692 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6073. Min Act: -0.1700
Data Index: 601395 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6073. Min Act: -0.1700
Data Index: 2616217 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7948. Min Range: -5.7948
Max Act: 5.6073. Min Act: -0.1700
Data Index: 843872 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19