Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.9626. Min Act: -0.1700
Data Index: 1869197 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.9626. Min Act: -0.1700
Data Index: 4147767 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.8688. Min Act: -0.1700
Data Index: 3113316 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.7751. Min Act: -0.1700
Data Index: 1507998 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.8063. Min Act: -0.1700
Data Index: 5561306 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.7438. Min Act: -0.1700
Data Index: 2321249 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.7438. Min Act: -0.1700
Data Index: 8032773 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.7125. Min Act: -0.1700
Data Index: 2349584 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6570069 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6500. Min Act: -0.1700
Data Index: 7733700 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 3890896 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 5642517 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6813. Min Act: -0.1700
Data Index: 7472738 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6188. Min Act: -0.1700
Data Index: 5991443 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6188. Min Act: -0.1700
Data Index: 563159 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.6188. Min Act: -0.1700
Data Index: 7529646 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.5875. Min Act: -0.1700
Data Index: 5561298 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.5875. Min Act: -0.1700
Data Index: 588715 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.5875. Min Act: -0.1700
Data Index: 8134312 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9626. Min Range: -4.9626
Max Act: 4.5563. Min Act: -0.1700
Data Index: 7511584 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19