Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.9765. Min Act: -0.1700
Data Index: 6028045 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.9765. Min Act: -0.1700
Data Index: 586377 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.9140. Min Act: -0.1700
Data Index: 5406597 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.8828. Min Act: -0.1700
Data Index: 4117231 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.8515. Min Act: -0.1700
Data Index: 5040395 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.8515. Min Act: -0.1700
Data Index: 3991341 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.7890. Min Act: -0.1700
Data Index: 430488 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.7890. Min Act: -0.1700
Data Index: 4236581 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.6953. Min Act: -0.1700
Data Index: 2106117 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.7265. Min Act: -0.1700
Data Index: 8083956 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.6328. Min Act: -0.1700
Data Index: 635752 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.6015. Min Act: -0.1700
Data Index: 8217022 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.6328. Min Act: -0.1700
Data Index: 8519791 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5703. Min Act: -0.1700
Data Index: 7039382 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5390. Min Act: -0.1700
Data Index: 5843325 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5703. Min Act: -0.1700
Data Index: 229908 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5390. Min Act: -0.1700
Data Index: 5130911 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5703. Min Act: -0.1700
Data Index: 185323 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5390. Min Act: -0.1700
Data Index: 7759221 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9765. Min Range: -6.9765
Max Act: 6.5078. Min Act: -0.1700
Data Index: 7990467 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19