Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5708 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9376. Min Range: -8.9376
Max Act: 8.9376. Min Act: -0.1700
Data Index: 6753664 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9376. Min Range: -8.9376
Max Act: 8.7501. Min Act: -0.1700
Data Index: 4483379 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9376. Min Range: -8.9376
Max Act: 8.1876. Min Act: -0.1700
Data Index: 7894806 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9376. Min Range: -8.9376
Max Act: 8.0001. Min Act: -0.1700
Data Index: 4587366 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.9376. Min Act: -0.1700
Data Index: 7893281 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.8126. Min Act: -0.1700
Data Index: 8540343 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.7814. Min Act: -0.1700
Data Index: 7189428 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.7814. Min Act: -0.1700
Data Index: 8270596 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.7189. Min Act: -0.1700
Data Index: 5585776 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.6876. Min Act: -0.1700
Data Index: 2544559 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.6251. Min Act: -0.1700
Data Index: 2711978 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5939. Min Act: -0.1700
Data Index: 2723262 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5939. Min Act: -0.1700
Data Index: 3101675 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5626. Min Act: -0.1700
Data Index: 6523083 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5626. Min Act: -0.1700
Data Index: 6796838 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5626. Min Act: -0.1700
Data Index: 7478010 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5314. Min Act: -0.1700
Data Index: 2470199 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.4689. Min Act: -0.1700
Data Index: 1701043 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.5001. Min Act: -0.1700
Data Index: 8041006 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9376. Min Range: -8.9376
Max Act: 7.4689. Min Act: -0.1700
Data Index: 3859527 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19