Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0176. Min Range: -8.0176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 1158212 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.8926. Min Act: -0.1700
Data Index: 7680524 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.8926. Min Act: -0.1700
Data Index: 5583870 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.8301. Min Act: -0.1700
Data Index: 3844047 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.8301. Min Act: -0.1700
Data Index: 2239910 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.7051. Min Act: -0.1700
Data Index: 3281424 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.5801. Min Act: -0.1700
Data Index: 2470699 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.6113. Min Act: -0.1700
Data Index: 4721736 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.5801. Min Act: -0.1700
Data Index: 7582934 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.5176. Min Act: -0.1700
Data Index: 8092024 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4863. Min Act: -0.1700
Data Index: 8519374 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4551. Min Act: -0.1700
Data Index: 6370515 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4551. Min Act: -0.1700
Data Index: 5640864 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4238. Min Act: -0.1700
Data Index: 3749528 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4238. Min Act: -0.1700
Data Index: 2546173 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4238. Min Act: -0.1700
Data Index: 265368 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.4238. Min Act: -0.1700
Data Index: 7135914 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.3926. Min Act: -0.1700
Data Index: 1021475 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.3926. Min Act: -0.1700
Data Index: 8501605 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0176. Min Range: -8.0176
Max Act: 7.3926. Min Act: -0.1700
Data Index: 2723912 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19