Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2599. Min Range: -6.2599
Max Act: 6.2599. Min Act: -0.1700
Data Index: 6469434 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2599. Min Range: -6.2599
Max Act: 6.1349. Min Act: -0.1700
Data Index: 2351962 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2599. Min Range: -6.2599
Max Act: 6.0724. Min Act: -0.1700
Data Index: 6814234 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2599. Min Range: -6.2599
Max Act: 6.0411. Min Act: -0.1700
Data Index: 6513684 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2599. Min Range: -6.2599
Max Act: 6.0099. Min Act: -0.1700
Data Index: 5713121 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.9161. Min Act: -0.1700
Data Index: 603869 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.9161. Min Act: -0.1700
Data Index: 589743 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8849. Min Act: -0.1700
Data Index: 758701 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8849. Min Act: -0.1700
Data Index: 3631296 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8849. Min Act: -0.1700
Data Index: 8678686 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8849. Min Act: -0.1700
Data Index: 7107008 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8224. Min Act: -0.1700
Data Index: 7736412 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8224. Min Act: -0.1700
Data Index: 3791184 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8224. Min Act: -0.1700
Data Index: 4190628 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.7911. Min Act: -0.1700
Data Index: 3405895 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8224. Min Act: -0.1700
Data Index: 5015876 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.8224. Min Act: -0.1700
Data Index: 1147903 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.7911. Min Act: -0.1700
Data Index: 3889214 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.7911. Min Act: -0.1700
Data Index: 3993044 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2599. Min Range: -6.2599
Max Act: 5.7911. Min Act: -0.1700
Data Index: 4753851 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19