Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4232046 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.6683. Min Act: -0.1700
Data Index: 998633 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.6996. Min Act: -0.1700
Data Index: 5261994 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.6058. Min Act: -0.1700
Data Index: 7392853 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.5746. Min Act: -0.1700
Data Index: 7909716 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.5746. Min Act: -0.1700
Data Index: 8750010 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4808. Min Act: -0.1700
Data Index: 4125373 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4808. Min Act: -0.1700
Data Index: 222501 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4808. Min Act: -0.1700
Data Index: 4703156 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4496. Min Act: -0.1700
Data Index: 4896316 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4183. Min Act: -0.1700
Data Index: 8450589 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.4183. Min Act: -0.1700
Data Index: 2395031 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3871. Min Act: -0.1700
Data Index: 7366154 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3871. Min Act: -0.1700
Data Index: 2961769 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3558. Min Act: -0.1700
Data Index: 5519123 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3558. Min Act: -0.1700
Data Index: 8049554 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3558. Min Act: -0.1700
Data Index: 8418941 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3246. Min Act: -0.1700
Data Index: 4214811 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3558. Min Act: -0.1700
Data Index: 6896463 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7308. Min Range: -6.7308
Max Act: 6.3246. Min Act: -0.1700
Data Index: 5090725 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19