Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.5143. Min Act: -0.1700
Data Index: 3346065 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.4830. Min Act: -0.1700
Data Index: 3430704 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.4518. Min Act: -0.1700
Data Index: 3671812 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.3893. Min Act: -0.1700
Data Index: 6390113 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.3267. Min Act: -0.1700
Data Index: 113451 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.3580. Min Act: -0.1700
Data Index: 3966673 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.2955. Min Act: -0.1700
Data Index: 6039706 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.2955. Min Act: -0.1700
Data Index: 5318975 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.2642. Min Act: -0.1700
Data Index: 3124408 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2325410 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1705. Min Act: -0.1700
Data Index: 6868788 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1705. Min Act: -0.1700
Data Index: 1228361 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1392. Min Act: -0.1700
Data Index: 2710 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1392. Min Act: -0.1700
Data Index: 4472193 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1392. Min Act: -0.1700
Data Index: 8384642 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1080. Min Act: -0.1700
Data Index: 7130168 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.0767. Min Act: -0.1700
Data Index: 5637908 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1080. Min Act: -0.1700
Data Index: 5246552 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.0767. Min Act: -0.1700
Data Index: 7658972 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5143. Min Range: -4.5143
Max Act: 4.1080. Min Act: -0.1700
Data Index: 7910710 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19