Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5486 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0550. Min Range: -5.0550
Max Act: 5.0550. Min Act: -0.1700
Data Index: 671149 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.7737. Min Act: -0.1700
Data Index: 3980169 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.7737. Min Act: -0.1700
Data Index: 6871247 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.7425. Min Act: -0.1700
Data Index: 6718113 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.7112. Min Act: -0.1700
Data Index: 8722230 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.6800. Min Act: -0.1700
Data Index: 4620122 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.6800. Min Act: -0.1700
Data Index: 1338166 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.6175. Min Act: -0.1700
Data Index: 3548159 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5862. Min Act: -0.1700
Data Index: 2054788 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5862. Min Act: -0.1700
Data Index: 6831321 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5550. Min Act: -0.1700
Data Index: 4169675 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 6120232 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 1448198 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 4977770 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.5237. Min Act: -0.1700
Data Index: 2059411 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.4925. Min Act: -0.1700
Data Index: 4169660 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.4925. Min Act: -0.1700
Data Index: 7296146 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.4612. Min Act: -0.1700
Data Index: 6343359 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.4612. Min Act: -0.1700
Data Index: 6118661 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0550. Min Range: -5.0550
Max Act: 4.4612. Min Act: -0.1700
Data Index: 3657005 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19