Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.9930. Min Act: -0.1700
Data Index: 1073630 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.9305. Min Act: -0.1700
Data Index: 577170 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.8055. Min Act: -0.1700
Data Index: 4533898 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.8055. Min Act: -0.1700
Data Index: 2279696 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.8055. Min Act: -0.1700
Data Index: 7788661 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7743. Min Act: -0.1700
Data Index: 7945581 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7430. Min Act: -0.1700
Data Index: 8171871 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7430. Min Act: -0.1700
Data Index: 2009951 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7118. Min Act: -0.1700
Data Index: 6318516 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7118. Min Act: -0.1700
Data Index: 2778800 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6805. Min Act: -0.1700
Data Index: 4150133 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.7430. Min Act: -0.1700
Data Index: 4571891 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6493. Min Act: -0.1700
Data Index: 65488 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6805. Min Act: -0.1700
Data Index: 7767922 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6805. Min Act: -0.1700
Data Index: 7512058 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6180. Min Act: -0.1700
Data Index: 3284285 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6180. Min Act: -0.1700
Data Index: 2134670 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6180. Min Act: -0.1700
Data Index: 6678365 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6180. Min Act: -0.1700
Data Index: 1196716 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9930. Min Range: -4.9930
Max Act: 4.6180. Min Act: -0.1700
Data Index: 3052712 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19