Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.5683. Min Act: -0.1700
Data Index: 6473999 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.5683. Min Act: -0.1700
Data Index: 3109030 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.3808. Min Act: -0.1700
Data Index: 7463995 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2870. Min Act: -0.1700
Data Index: 8524794 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.3183. Min Act: -0.1700
Data Index: 3078589 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2870. Min Act: -0.1700
Data Index: 8400980 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2870. Min Act: -0.1700
Data Index: 1327397 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2245. Min Act: -0.1700
Data Index: 6710073 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2245. Min Act: -0.1700
Data Index: 5981955 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.1933. Min Act: -0.1700
Data Index: 2013339 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2245. Min Act: -0.1700
Data Index: 1898416 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.1620. Min Act: -0.1700
Data Index: 4019034 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.1933. Min Act: -0.1700
Data Index: 4052400 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.2245. Min Act: -0.1700
Data Index: 1068710 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.0995. Min Act: -0.1700
Data Index: 314606 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.1620. Min Act: -0.1700
Data Index: 5032994 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.0995. Min Act: -0.1700
Data Index: 1924381 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.0995. Min Act: -0.1700
Data Index: 3741873 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.0683. Min Act: -0.1700
Data Index: 4713087 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5683. Min Range: -7.5683
Max Act: 7.0683. Min Act: -0.1700
Data Index: 4166654 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19