Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.9741. Min Act: -0.1700
Data Index: 3589952 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.9116. Min Act: -0.1700
Data Index: 7191066 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8491. Min Act: -0.1700
Data Index: 3400919 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8491. Min Act: -0.1700
Data Index: 2606995 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8491. Min Act: -0.1700
Data Index: 4293239 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8178. Min Act: -0.1700
Data Index: 1813286 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8178. Min Act: -0.1700
Data Index: 7700218 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.8178. Min Act: -0.1700
Data Index: 8603080 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.7553. Min Act: -0.1700
Data Index: 2999597 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.7553. Min Act: -0.1700
Data Index: 4421290 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.7553. Min Act: -0.1700
Data Index: 548993 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.7553. Min Act: -0.1700
Data Index: 118722 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1660634 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.6928. Min Act: -0.1700
Data Index: 3142620 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.6928. Min Act: -0.1700
Data Index: 1336049 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.6303. Min Act: -0.1700
Data Index: 419478 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.6303. Min Act: -0.1700
Data Index: 5273342 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.5991. Min Act: -0.1700
Data Index: 6207808 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.5991. Min Act: -0.1700
Data Index: 4422014 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9741. Min Range: -7.9741
Max Act: 7.5991. Min Act: -0.1700
Data Index: 4443330 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19