Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.6724. Min Act: -0.1700
Data Index: 526930 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.5474. Min Act: -0.1700
Data Index: 8730685 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.3599. Min Act: -0.1700
Data Index: 979737 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.3599. Min Act: -0.1700
Data Index: 799812 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.3287. Min Act: -0.1700
Data Index: 5598076 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2974. Min Act: -0.1700
Data Index: 7248636 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2349. Min Act: -0.1700
Data Index: 5040048 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2349. Min Act: -0.1700
Data Index: 5150313 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2349. Min Act: -0.1700
Data Index: 1361452 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2037. Min Act: -0.1700
Data Index: 4588752 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2349. Min Act: -0.1700
Data Index: 4057988 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2037. Min Act: -0.1700
Data Index: 2626823 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2037. Min Act: -0.1700
Data Index: 7515660 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.2037. Min Act: -0.1700
Data Index: 4016227 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1724. Min Act: -0.1700
Data Index: 7496866 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1412. Min Act: -0.1700
Data Index: 2255861 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1412. Min Act: -0.1700
Data Index: 5816409 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1724. Min Act: -0.1700
Data Index: 5263172 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1724. Min Act: -0.1700
Data Index: 445828 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6724. Min Range: -5.6724
Max Act: 5.1412. Min Act: -0.1700
Data Index: 7905431 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19