Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4629 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.9101. Min Act: -0.1700
Data Index: 2126868 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.9101. Min Act: -0.1700
Data Index: 8810014 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8466. Min Act: -0.1700
Data Index: 8392181 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8307. Min Act: -0.1700
Data Index: 3870558 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7989. Min Act: -0.1700
Data Index: 3872517 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8148. Min Act: -0.1700
Data Index: 5014665 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8148. Min Act: -0.1700
Data Index: 6969511 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8148. Min Act: -0.1700
Data Index: 8166219 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.8148. Min Act: -0.1700
Data Index: 4932158 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7989. Min Act: -0.1700
Data Index: 6802847 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 3674551 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7989. Min Act: -0.1700
Data Index: 1459376 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 1163512 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 775411 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 5801312 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 5801313 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7989. Min Act: -0.1700
Data Index: 5014663 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 7647295 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7989. Min Act: -0.1700
Data Index: 423829 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9101. Min Range: -2.9101
Max Act: 2.7830. Min Act: -0.1700
Data Index: 7044804 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19