Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5816 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.9082. Min Act: -0.1700
Data Index: 658583 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.7832. Min Act: -0.1700
Data Index: 5091908 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.7207. Min Act: -0.1700
Data Index: 2068717 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.6582. Min Act: -0.1700
Data Index: 5254170 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.5957. Min Act: -0.1700
Data Index: 5572658 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.5957. Min Act: -0.1700
Data Index: 132384 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.5332. Min Act: -0.1700
Data Index: 5691061 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.4082. Min Act: -0.1700
Data Index: 7869003 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.2832. Min Act: -0.1700
Data Index: 4488288 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.2832. Min Act: -0.1700
Data Index: 5091065 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.1582. Min Act: -0.1700
Data Index: 6777408 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.0957. Min Act: -0.1700
Data Index: 6730151 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.0332. Min Act: -0.1700
Data Index: 6341234 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.0332. Min Act: -0.1700
Data Index: 6830053 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9082. Min Range: -8.9082
Max Act: 8.0332. Min Act: -0.1700
Data Index: 6716325 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9082. Min Range: -8.9082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 2899717 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9082. Min Range: -8.9082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 7127942 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9082. Min Range: -8.9082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 5676349 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9082. Min Range: -8.9082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 4308363 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9082. Min Range: -8.9082
Max Act: 7.9707. Min Act: -0.1700
Data Index: 283408 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19