Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.1558. Min Act: -0.1700
Data Index: 7092959 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5837393 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1558. Min Range: -5.1558
Max Act: 5.0933. Min Act: -0.1700
Data Index: 4764869 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9996. Min Act: -0.1700
Data Index: 4126794 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9683. Min Act: -0.1700
Data Index: 6947484 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9371. Min Act: -0.1700
Data Index: 8721975 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3302098 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7010163 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8121. Min Act: -0.1700
Data Index: 7257364 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8121. Min Act: -0.1700
Data Index: 2678918 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8121. Min Act: -0.1700
Data Index: 5922416 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.8121. Min Act: -0.1700
Data Index: 2678913 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7808. Min Act: -0.1700
Data Index: 4749905 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7808. Min Act: -0.1700
Data Index: 7041863 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7808. Min Act: -0.1700
Data Index: 4425245 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7496. Min Act: -0.1700
Data Index: 2678916 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7496. Min Act: -0.1700
Data Index: 6254592 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7496. Min Act: -0.1700
Data Index: 851068 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7183. Min Act: -0.1700
Data Index: 2678908 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1558. Min Range: -5.1558
Max Act: 4.7496. Min Act: -0.1700
Data Index: 5543545 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19