Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2894. Min Range: -7.2894
Max Act: 7.2894. Min Act: -0.1700
Data Index: 7068494 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9769. Min Act: -0.1700
Data Index: 3538518 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9457. Min Act: -0.1700
Data Index: 1027896 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9457. Min Act: -0.1700
Data Index: 8043437 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1273880 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1650228 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.9144. Min Act: -0.1700
Data Index: 6957620 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.8832. Min Act: -0.1700
Data Index: 3663231 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.8519. Min Act: -0.1700
Data Index: 8519715 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.8519. Min Act: -0.1700
Data Index: 613176 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.8207. Min Act: -0.1700
Data Index: 6220283 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.7894. Min Act: -0.1700
Data Index: 2560330 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.7894. Min Act: -0.1700
Data Index: 2865607 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.7269. Min Act: -0.1700
Data Index: 2531401 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.6957. Min Act: -0.1700
Data Index: 6247076 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.6957. Min Act: -0.1700
Data Index: 5172851 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.7269. Min Act: -0.1700
Data Index: 4831729 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.6644. Min Act: -0.1700
Data Index: 7327026 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.6332. Min Act: -0.1700
Data Index: 403792 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2894. Min Range: -7.2894
Max Act: 6.6332. Min Act: -0.1700
Data Index: 3704367 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19