Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.5165. Min Act: -0.1700
Data Index: 5872000 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.3914. Min Act: -0.1700
Data Index: 458046 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2977. Min Act: -0.1700
Data Index: 3537295 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2977. Min Act: -0.1700
Data Index: 4520476 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2039. Min Act: -0.1700
Data Index: 6452493 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2352. Min Act: -0.1700
Data Index: 4682108 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2039. Min Act: -0.1700
Data Index: 6271076 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.2039. Min Act: -0.1700
Data Index: 3820883 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.1414. Min Act: -0.1700
Data Index: 5014163 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.1102. Min Act: -0.1700
Data Index: 8429800 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.1102. Min Act: -0.1700
Data Index: 5686057 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 5014164 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 4079231 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 8054111 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 5077190 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 7660938 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0789. Min Act: -0.1700
Data Index: 6953094 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0476. Min Act: -0.1700
Data Index: 2939942 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0476. Min Act: -0.1700
Data Index: 6725299 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5165. Min Range: -4.5165
Max Act: 4.0476. Min Act: -0.1700
Data Index: 5872014 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19