Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.9851. Min Act: -0.1700
Data Index: 4970145 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.7664. Min Act: -0.1698
Data Index: 4066590 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.6726. Min Act: -0.1699
Data Index: 783952 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.6101. Min Act: -0.1700
Data Index: 920426 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.6101. Min Act: -0.1700
Data Index: 4066592 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.5789. Min Act: -0.1696
Data Index: 8006025 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.5789. Min Act: -0.1699
Data Index: 4066591 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.5476. Min Act: -0.1700
Data Index: 4011234 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4695. Min Act: -0.1635
Data Index: 1977585 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4383. Min Act: -0.1700
Data Index: 239311 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4539. Min Act: -0.1700
Data Index: 2071332 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4226. Min Act: -0.1685
Data Index: 3349363 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4226. Min Act: -0.1700
Data Index: 4893996 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.4070. Min Act: -0.1700
Data Index: 6530150 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3914. Min Act: -0.1699
Data Index: 6131087 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3757. Min Act: -0.1700
Data Index: 2173752 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3757. Min Act: -0.1700
Data Index: 2345409 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3757. Min Act: -0.1696
Data Index: 4188772 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3601. Min Act: -0.1700
Data Index: 4495679 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9851. Min Range: -4.9851
Max Act: 4.3289. Min Act: -0.1700
Data Index: 2720486 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19