Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.9300. Min Act: -0.1700
Data Index: 5048874 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.9300. Min Act: -0.1700
Data Index: 5048887 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8988. Min Act: -0.1700
Data Index: 8516774 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8675. Min Act: -0.1700
Data Index: 5048861 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8988. Min Act: -0.1700
Data Index: 4297158 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8675. Min Act: -0.1700
Data Index: 5048883 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8675. Min Act: -0.1700
Data Index: 5992790 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8363. Min Act: -0.1700
Data Index: 5048871 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8050. Min Act: -0.1700
Data Index: 5048886 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8363. Min Act: -0.1700
Data Index: 5048885 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.8050. Min Act: -0.1700
Data Index: 5048893 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7738. Min Act: -0.1700
Data Index: 5048900 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7738. Min Act: -0.1700
Data Index: 5048867 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7738. Min Act: -0.1700
Data Index: 8430650 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7113. Min Act: -0.1700
Data Index: 3100473 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.7113. Min Act: -0.1700
Data Index: 5048897 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6800. Min Act: -0.1700
Data Index: 5048901 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6800. Min Act: -0.1700
Data Index: 5992789 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6800. Min Act: -0.1700
Data Index: 1280891 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9300. Min Range: -6.9300
Max Act: 6.6488. Min Act: -0.1700
Data Index: 5048875 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19