Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1019. Min Range: -8.1019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 7660636 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1019. Min Range: -8.1019
Max Act: 8.1019. Min Act: -0.1700
Data Index: 3493043 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.9144. Min Act: -0.1700
Data Index: 7851039 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.8519. Min Act: -0.1700
Data Index: 6379049 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.8519. Min Act: -0.1700
Data Index: 3121253 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7894. Min Act: -0.1700
Data Index: 7784345 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7894. Min Act: -0.1700
Data Index: 7749372 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7269. Min Act: -0.1700
Data Index: 6682736 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7269. Min Act: -0.1700
Data Index: 3768706 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.7269. Min Act: -0.1700
Data Index: 7410585 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 1874681 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 1624738 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 8069394 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 2091388 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6644. Min Act: -0.1700
Data Index: 6691460 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 3930126 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 4209850 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 1923105 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 350425 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1019. Min Range: -8.1019
Max Act: 7.6019. Min Act: -0.1700
Data Index: 1044950 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19