Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 7836632 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.2035. Min Act: -0.1700
Data Index: 179089 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.1723. Min Act: -0.1700
Data Index: 3751067 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.1410. Min Act: -0.1700
Data Index: 5200694 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.1410. Min Act: -0.1700
Data Index: 1577017 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.1098. Min Act: -0.1700
Data Index: 5324014 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.1098. Min Act: -0.1700
Data Index: 6326992 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0473. Min Act: -0.1700
Data Index: 2560292 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0785. Min Act: -0.1700
Data Index: 7534201 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0473. Min Act: -0.1700
Data Index: 6299540 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0473. Min Act: -0.1700
Data Index: 6896574 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0473. Min Act: -0.1700
Data Index: 3856025 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0473. Min Act: -0.1700
Data Index: 4231584 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2035. Min Range: -5.2035
Max Act: 5.0160. Min Act: -0.1700
Data Index: 5512614 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9848. Min Act: -0.1700
Data Index: 6368971 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9848. Min Act: -0.1700
Data Index: 5573873 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9535. Min Act: -0.1700
Data Index: 6905862 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9535. Min Act: -0.1700
Data Index: 2952915 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9535. Min Act: -0.1700
Data Index: 8767288 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2035. Min Range: -5.2035
Max Act: 4.9223. Min Act: -0.1700
Data Index: 6774585 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19