Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.3344. Min Act: -0.1700
Data Index: 5046076 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.1781. Min Act: -0.1700
Data Index: 7365299 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.1469. Min Act: -0.1700
Data Index: 4959353 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.1469. Min Act: -0.1700
Data Index: 4023433 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.1469. Min Act: -0.1700
Data Index: 106086 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.0531. Min Act: -0.1700
Data Index: 3792699 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.0531. Min Act: -0.1700
Data Index: 5925317 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.0531. Min Act: -0.1700
Data Index: 4602791 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.0219. Min Act: -0.1700
Data Index: 1353153 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3344. Min Range: -6.3344
Max Act: 6.0219. Min Act: -0.1700
Data Index: 1275009 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9594. Min Act: -0.1700
Data Index: 6029892 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9906. Min Act: -0.1700
Data Index: 4497750 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9594. Min Act: -0.1700
Data Index: 8534659 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9906. Min Act: -0.1700
Data Index: 3029432 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9281. Min Act: -0.1700
Data Index: 1774554 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9594. Min Act: -0.1700
Data Index: 7641002 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9281. Min Act: -0.1700
Data Index: 832911 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9281. Min Act: -0.1700
Data Index: 7859184 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.9281. Min Act: -0.1700
Data Index: 2611175 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3344. Min Range: -6.3344
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5197135 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19