Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1531. Min Range: -7.1531
Max Act: 7.1531. Min Act: -0.1700
Data Index: 1290628 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.9344. Min Act: -0.1700
Data Index: 8399420 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.9656. Min Act: -0.1700
Data Index: 1290629 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.9031. Min Act: -0.1700
Data Index: 3149050 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.9344. Min Act: -0.1700
Data Index: 7412810 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.8719. Min Act: -0.1700
Data Index: 1000195 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.8719. Min Act: -0.1700
Data Index: 7412813 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.8406. Min Act: -0.1700
Data Index: 8427181 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.8406. Min Act: -0.1700
Data Index: 2072163 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.8094. Min Act: -0.1700
Data Index: 1290632 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6844. Min Act: -0.1700
Data Index: 2353070 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.7156. Min Act: -0.1700
Data Index: 5702708 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6844. Min Act: -0.1700
Data Index: 5204122 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6531. Min Act: -0.1700
Data Index: 5702705 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6531. Min Act: -0.1700
Data Index: 1000189 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6219. Min Act: -0.1700
Data Index: 7412814 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6219. Min Act: -0.1700
Data Index: 4434917 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6531. Min Act: -0.1700
Data Index: 1000194 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6219. Min Act: -0.1700
Data Index: 4434915 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1531. Min Range: -7.1531
Max Act: 6.6219. Min Act: -0.1700
Data Index: 4277108 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19