Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5435 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2837. Min Range: -8.2837
Max Act: 8.2837. Min Act: -0.1700
Data Index: 1733024 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.7837. Min Act: -0.1700
Data Index: 7721970 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.7212. Min Act: -0.1700
Data Index: 2994330 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.7212. Min Act: -0.1700
Data Index: 2584507 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.7212. Min Act: -0.1700
Data Index: 186193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.7212. Min Act: -0.1700
Data Index: 6242611 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.6587. Min Act: -0.1700
Data Index: 7698968 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.6587. Min Act: -0.1700
Data Index: 217925 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.6587. Min Act: -0.1700
Data Index: 8649585 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.6587. Min Act: -0.1700
Data Index: 3253423 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.6587. Min Act: -0.1700
Data Index: 6535063 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 6226370 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 3298171 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 1744921 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 6679341 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 8490442 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5962. Min Act: -0.1700
Data Index: 5494843 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5337. Min Act: -0.1700
Data Index: 8122889 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5337. Min Act: -0.1700
Data Index: 1743418 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2837. Min Range: -8.2837
Max Act: 7.5337. Min Act: -0.1700
Data Index: 6648968 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19