Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.1674. Min Act: -0.1700
Data Index: 818219 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.1362. Min Act: -0.1700
Data Index: 5434407 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.1049. Min Act: -0.1700
Data Index: 3371838 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0736. Min Act: -0.1700
Data Index: 2325092 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0424. Min Act: -0.1700
Data Index: 2935895 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0424. Min Act: -0.1700
Data Index: 971963 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0736. Min Act: -0.1700
Data Index: 5174736 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0111. Min Act: -0.1700
Data Index: 4715321 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0111. Min Act: -0.1700
Data Index: 1020771 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0424. Min Act: -0.1700
Data Index: 3079634 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0736. Min Act: -0.1700
Data Index: 6195764 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0424. Min Act: -0.1700
Data Index: 7344093 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9799. Min Act: -0.1700
Data Index: 703154 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9799. Min Act: -0.1700
Data Index: 3613615 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1674. Min Range: -4.1674
Max Act: 4.0111. Min Act: -0.1700
Data Index: 3493104 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9486. Min Act: -0.1700
Data Index: 616478 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9486. Min Act: -0.1700
Data Index: 2451871 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9486. Min Act: -0.1700
Data Index: 3444526 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9799. Min Act: -0.1700
Data Index: 5678651 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1674. Min Range: -4.1674
Max Act: 3.9799. Min Act: -0.1700
Data Index: 5531915 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19