Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6259 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0953. Min Range: -6.0953
Max Act: 6.0953. Min Act: -0.1700
Data Index: 5795334 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.9391. Min Act: -0.1700
Data Index: 4246312 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4184495 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.7516. Min Act: -0.1700
Data Index: 2463103 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4668025 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6891. Min Act: -0.1700
Data Index: 2991687 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.7203. Min Act: -0.1699
Data Index: 6565628 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6891. Min Act: -0.1700
Data Index: 885649 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6578. Min Act: -0.1700
Data Index: 6957112 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6266. Min Act: -0.1700
Data Index: 6588821 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6266. Min Act: -0.1700
Data Index: 5800908 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6266. Min Act: -0.1700
Data Index: 3051786 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6266. Min Act: -0.1700
Data Index: 4492722 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.6578. Min Act: -0.1700
Data Index: 3757295 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 4902138 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 4859853 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 3068357 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 6300392 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5641. Min Act: -0.1700
Data Index: 4184498 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0953. Min Range: -6.0953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 2204035 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19