Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0009. Min Range: -8.0009
Max Act: 8.0009. Min Act: -0.1700
Data Index: 6802142 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.8759. Min Act: -0.1700
Data Index: 4480502 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.8134. Min Act: -0.1700
Data Index: 5053703 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.8134. Min Act: -0.1700
Data Index: 5431508 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.8134. Min Act: -0.1700
Data Index: 5043803 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.8134. Min Act: -0.1700
Data Index: 1133948 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 3334615 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 6113497 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 4907084 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 5768525 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 7976463 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 4831166 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 677977 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 4558488 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.7509. Min Act: -0.1700
Data Index: 7280672 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.6884. Min Act: -0.1700
Data Index: 718563 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.6884. Min Act: -0.1700
Data Index: 1221764 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.6884. Min Act: -0.1700
Data Index: 2738957 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.6884. Min Act: -0.1700
Data Index: 3009552 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0009. Min Range: -8.0009
Max Act: 7.6884. Min Act: -0.1700
Data Index: 7200633 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19