Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 803 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.9323. Min Act: -0.1700
Data Index: 1522442 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.9323. Min Act: -0.1700
Data Index: 632962 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.8073. Min Act: -0.1700
Data Index: 4130644 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.8073. Min Act: -0.1700
Data Index: 3357576 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.7760. Min Act: -0.1700
Data Index: 7122537 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.7760. Min Act: -0.1700
Data Index: 7972726 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.7760. Min Act: -0.1700
Data Index: 4762068 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.7448. Min Act: -0.1700
Data Index: 5871024 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.7135. Min Act: -0.1700
Data Index: 1537370 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.6823. Min Act: -0.1700
Data Index: 2964005 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.6823. Min Act: -0.1700
Data Index: 1722358 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.6823. Min Act: -0.1700
Data Index: 2759144 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.6823. Min Act: -0.1700
Data Index: 114129 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.6198. Min Act: -0.1700
Data Index: 3670988 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5885. Min Act: -0.1700
Data Index: 8179678 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5885. Min Act: -0.1700
Data Index: 2702021 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5573. Min Act: -0.1700
Data Index: 8004074 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5573. Min Act: -0.1700
Data Index: 2954295 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.5260. Min Act: -0.1700
Data Index: 5309325 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9323. Min Range: -6.9323
Max Act: 6.4948. Min Act: -0.1700
Data Index: 8043850 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19