Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0951. Min Range: -8.0951
Max Act: 8.0951. Min Act: -0.1700
Data Index: 6058947 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.9076. Min Act: -0.1700
Data Index: 4672815 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.6576. Min Act: -0.1700
Data Index: 4672824 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.6576. Min Act: -0.1700
Data Index: 5441492 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.6576. Min Act: -0.1700
Data Index: 286872 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.5951. Min Act: -0.1700
Data Index: 3339679 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.5326. Min Act: -0.1700
Data Index: 4552745 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.5326. Min Act: -0.1700
Data Index: 2133182 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.5014. Min Act: -0.1700
Data Index: 175092 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.5014. Min Act: -0.1700
Data Index: 3533677 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.4389. Min Act: -0.1700
Data Index: 105273 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.4389. Min Act: -0.1700
Data Index: 6619883 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3764. Min Act: -0.1700
Data Index: 8306953 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.4076. Min Act: -0.1700
Data Index: 2726198 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.4076. Min Act: -0.1700
Data Index: 8113391 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3451. Min Act: -0.1700
Data Index: 3135216 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3764. Min Act: -0.1700
Data Index: 7922047 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3139. Min Act: -0.1700
Data Index: 4073075 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3764. Min Act: -0.1700
Data Index: 2646953 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0951. Min Range: -8.0951
Max Act: 7.3451. Min Act: -0.1700
Data Index: 7015032 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19