Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4261 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0621. Min Act: -0.1700
Data Index: 3040289 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0621. Min Act: -0.1700
Data Index: 613681 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0621. Min Act: -0.1700
Data Index: 2025771 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0308. Min Act: -0.1700
Data Index: 3693863 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0308. Min Act: -0.1700
Data Index: 329099 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0308. Min Act: -0.1700
Data Index: 3901686 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0308. Min Act: -0.1700
Data Index: 2656084 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 3789414 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0621. Min Act: -0.1700
Data Index: 1244606 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0621. Min Range: -4.0621
Max Act: 4.0308. Min Act: -0.1700
Data Index: 3311677 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 2397258 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 1093294 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 7908582 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 6022590 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 4136367 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9996. Min Act: -0.1700
Data Index: 835538 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9683. Min Act: -0.1700
Data Index: 2460151 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9683. Min Act: -0.1700
Data Index: 5146625 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9683. Min Act: -0.1700
Data Index: 5249512 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0621. Min Range: -4.0621
Max Act: 3.9683. Min Act: -0.1700
Data Index: 5282821 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19