Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7128. Min Range: -6.7128
Max Act: 6.7128. Min Act: -0.1700
Data Index: 7123288 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7128. Min Range: -6.7128
Max Act: 6.4941. Min Act: -0.1700
Data Index: 1150752 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7128. Min Range: -6.7128
Max Act: 6.4003. Min Act: -0.1700
Data Index: 2362920 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7128. Min Range: -6.7128
Max Act: 6.1191. Min Act: -0.1700
Data Index: 3099152 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.9941. Min Act: -0.1700
Data Index: 4485326 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.9628. Min Act: -0.1700
Data Index: 5957131 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.9628. Min Act: -0.1700
Data Index: 3291821 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.9316. Min Act: -0.1700
Data Index: 3057871 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.9316. Min Act: -0.1700
Data Index: 6270099 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8691. Min Act: -0.1700
Data Index: 4130604 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8378. Min Act: -0.1700
Data Index: 8017367 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8378. Min Act: -0.1700
Data Index: 2494130 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2161285 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8066. Min Act: -0.1700
Data Index: 3355586 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2046770 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.7753. Min Act: -0.1700
Data Index: 2774769 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.7753. Min Act: -0.1700
Data Index: 6125373 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.7753. Min Act: -0.1700
Data Index: 6130444 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.7753. Min Act: -0.1700
Data Index: 6137795 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7128. Min Range: -6.7128
Max Act: 5.7753. Min Act: -0.1700
Data Index: 2545851 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19