Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3873. Min Act: -0.1700
Data Index: 4039147 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3873. Min Act: -0.1700
Data Index: 6480779 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3873. Min Act: -0.1700
Data Index: 4057874 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3873. Min Act: -0.1700
Data Index: 4252293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3873. Min Act: -0.1700
Data Index: 1114331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 6534586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 6849696 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 7723371 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 8543275 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 2953507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 1836657 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3559. Min Act: -0.1700
Data Index: 5531801 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 1885479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 6295969 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 2754261 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 2547660 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 5350004 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 4887820 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 4873903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3873. Min Range: -3.3873
Max Act: 3.3245. Min Act: -0.1700
Data Index: 1490352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19