Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.2785. Min Act: -0.1700
Data Index: 4306390 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.0910. Min Act: -0.1700
Data Index: 2318466 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.0910. Min Act: -0.1700
Data Index: 6561175 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.0597. Min Act: -0.1700
Data Index: 827265 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.0285. Min Act: -0.1700
Data Index: 4739622 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2785. Min Range: -7.2785
Max Act: 7.0285. Min Act: -0.1700
Data Index: 843942 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.9972. Min Act: -0.1700
Data Index: 2457290 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.9660. Min Act: -0.1700
Data Index: 524546 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.9660. Min Act: -0.1700
Data Index: 4034247 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.9035. Min Act: -0.1700
Data Index: 1216765 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.9347. Min Act: -0.1700
Data Index: 8071749 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8722. Min Act: -0.1700
Data Index: 6554848 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8722. Min Act: -0.1700
Data Index: 4134274 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8722. Min Act: -0.1700
Data Index: 6550772 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8722. Min Act: -0.1700
Data Index: 8170564 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8410. Min Act: -0.1700
Data Index: 621198 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8722. Min Act: -0.1700
Data Index: 4729464 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8410. Min Act: -0.1700
Data Index: 120323 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8410. Min Act: -0.1700
Data Index: 29986 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2785. Min Range: -7.2785
Max Act: 6.8410. Min Act: -0.1700
Data Index: 3012436 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19