Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.9027. Min Act: -0.1700
Data Index: 5429383 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.8714. Min Act: -0.1700
Data Index: 160979 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.8714. Min Act: -0.1700
Data Index: 7834908 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.8714. Min Act: -0.1700
Data Index: 1875334 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.8089. Min Act: -0.1700
Data Index: 6473895 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.7464. Min Act: -0.1700
Data Index: 3158282 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.7152. Min Act: -0.1700
Data Index: 2105628 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6839. Min Act: -0.1700
Data Index: 7197717 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6839. Min Act: -0.1700
Data Index: 1686916 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.7152. Min Act: -0.1700
Data Index: 1003541 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 7954250 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 6603417 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6214. Min Act: -0.1700
Data Index: 8057741 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6214. Min Act: -0.1700
Data Index: 4336841 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6214. Min Act: -0.1700
Data Index: 3774359 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 8553335 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6214. Min Act: -0.1700
Data Index: 5285642 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6214. Min Act: -0.1700
Data Index: 5618372 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6527. Min Act: -0.1700
Data Index: 3459524 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 4647650 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19