Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0919. Min Range: -6.0919
Max Act: 6.0919. Min Act: -0.1700
Data Index: 5219054 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.9357. Min Act: -0.1700
Data Index: 4783686 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.9357. Min Act: -0.1700
Data Index: 3666929 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.9044. Min Act: -0.1700
Data Index: 970794 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.8732. Min Act: -0.1700
Data Index: 3688106 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.8419. Min Act: -0.1700
Data Index: 361218 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.8107. Min Act: -0.1700
Data Index: 763967 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.8107. Min Act: -0.1700
Data Index: 6960456 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7482. Min Act: -0.1700
Data Index: 2892728 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7794. Min Act: -0.1700
Data Index: 4358956 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7482. Min Act: -0.1700
Data Index: 4956145 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7482. Min Act: -0.1700
Data Index: 1367514 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7482. Min Act: -0.1700
Data Index: 691072 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7169. Min Act: -0.1700
Data Index: 6467114 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.7169. Min Act: -0.1700
Data Index: 3626114 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.6857. Min Act: -0.1700
Data Index: 6165942 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.6857. Min Act: -0.1700
Data Index: 2727405 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.6544. Min Act: -0.1700
Data Index: 8660637 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.6544. Min Act: -0.1700
Data Index: 6657284 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0919. Min Range: -6.0919
Max Act: 5.6857. Min Act: -0.1700
Data Index: 3176158 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19