Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.9230. Min Act: -0.1700
Data Index: 8224683 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.8917. Min Act: -0.1700
Data Index: 4484572 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2933267 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.8292. Min Act: -0.1700
Data Index: 434498 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.8292. Min Act: -0.1700
Data Index: 5133265 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3794690 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7980. Min Act: -0.1700
Data Index: 7575979 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7355. Min Act: -0.1700
Data Index: 7555738 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7355. Min Act: -0.1700
Data Index: 3266684 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7355. Min Act: -0.1700
Data Index: 488098 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.7355. Min Act: -0.1700
Data Index: 2440420 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6730. Min Act: -0.1700
Data Index: 1109701 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6730. Min Act: -0.1700
Data Index: 7026362 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6105. Min Act: -0.1700
Data Index: 3034030 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6417. Min Act: -0.1700
Data Index: 3882384 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6417. Min Act: -0.1700
Data Index: 5566608 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6105. Min Act: -0.1700
Data Index: 4527695 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6105. Min Act: -0.1700
Data Index: 7660961 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6105. Min Act: -0.1700
Data Index: 6472675 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9230. Min Range: -5.9230
Max Act: 5.6105. Min Act: -0.1700
Data Index: 1410792 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19