Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4952 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.3814. Min Act: -0.1700
Data Index: 8341892 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.3502. Min Act: -0.1700
Data Index: 8397059 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.2252. Min Act: -0.1700
Data Index: 7966096 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1524253 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.1314. Min Act: -0.1700
Data Index: 4597955 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.1002. Min Act: -0.1700
Data Index: 2570103 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.1002. Min Act: -0.1700
Data Index: 1460771 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.0377. Min Act: -0.1700
Data Index: 8525099 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3814. Min Range: -5.3814
Max Act: 5.0064. Min Act: -0.1700
Data Index: 8165602 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9752. Min Act: -0.1700
Data Index: 8771447 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9752. Min Act: -0.1700
Data Index: 487919 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9752. Min Act: -0.1700
Data Index: 6273722 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9439. Min Act: -0.1700
Data Index: 2779189 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9439. Min Act: -0.1700
Data Index: 524605 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9439. Min Act: -0.1700
Data Index: 5585447 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9439. Min Act: -0.1700
Data Index: 426819 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9439. Min Act: -0.1700
Data Index: 4255148 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9127. Min Act: -0.1700
Data Index: 2396261 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.9127. Min Act: -0.1700
Data Index: 7944127 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3814. Min Range: -5.3814
Max Act: 4.8814. Min Act: -0.1700
Data Index: 4105902 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19