Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.6908. Min Act: -0.1700
Data Index: 6996583 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.4095. Min Act: -0.1700
Data Index: 5871253 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.2532. Min Act: -0.1700
Data Index: 830006 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.2532. Min Act: -0.1700
Data Index: 1961833 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.2532. Min Act: -0.1700
Data Index: 1864266 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.2220. Min Act: -0.1700
Data Index: 8765223 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 2949434 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4283565 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 5587039 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4073959 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 987944 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 6976857 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4645174 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1595. Min Act: -0.1700
Data Index: 1023814 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1595. Min Act: -0.1700
Data Index: 3203977 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5210108 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1595. Min Act: -0.1700
Data Index: 5037645 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1282. Min Act: -0.1700
Data Index: 6365331 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.0970. Min Act: -0.1700
Data Index: 3580338 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6908. Min Range: -4.6908
Max Act: 4.1282. Min Act: -0.1700
Data Index: 1071637 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19