Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1302. Min Range: -8.1302
Max Act: 8.1302. Min Act: -0.1700
Data Index: 8375214 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1302. Min Range: -8.1302
Max Act: 8.0052. Min Act: -0.1700
Data Index: 6358511 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.9427. Min Act: -0.1700
Data Index: 2342366 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.8802. Min Act: -0.1700
Data Index: 3082618 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.9427. Min Act: -0.1700
Data Index: 422685 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.8802. Min Act: -0.1700
Data Index: 5286166 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.8802. Min Act: -0.1700
Data Index: 6783791 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.8802. Min Act: -0.1700
Data Index: 6378554 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.8177. Min Act: -0.1700
Data Index: 1893245 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 4899497 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 3599517 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 2005831 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 3429559 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 5231010 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 7722521 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.7552. Min Act: -0.1700
Data Index: 4543692 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.6927. Min Act: -0.1700
Data Index: 8203567 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.6927. Min Act: -0.1700
Data Index: 8531030 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.6302. Min Act: -0.1700
Data Index: 761902 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1302. Min Range: -8.1302
Max Act: 7.6927. Min Act: -0.1700
Data Index: 6306638 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19