Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0837. Min Act: -0.1700
Data Index: 104188 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0995. Min Act: -0.1700
Data Index: 6246671 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0679. Min Act: -0.1700
Data Index: 4220626 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0679. Min Act: -0.1700
Data Index: 4022553 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0522. Min Act: -0.1700
Data Index: 547804 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0995. Min Range: -3.0995
Max Act: 3.0522. Min Act: -0.1700
Data Index: 1534581 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9890. Min Act: -0.1700
Data Index: 7122783 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9890. Min Act: -0.1700
Data Index: 1534580 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9890. Min Act: -0.1700
Data Index: 6345629 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9890. Min Act: -0.1700
Data Index: 5338949 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9732. Min Act: -0.1700
Data Index: 4517172 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9573. Min Act: -0.1700
Data Index: 7273167 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9573. Min Act: -0.1700
Data Index: 5572104 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9573. Min Act: -0.1700
Data Index: 3939919 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9573. Min Act: -0.1700
Data Index: 3258077 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9415. Min Act: -0.1700
Data Index: 739105 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9415. Min Act: -0.1700
Data Index: 3730413 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9415. Min Act: -0.1700
Data Index: 1234549 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9415. Min Act: -0.1700
Data Index: 4517161 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0995. Min Range: -3.0995
Max Act: 2.9415. Min Act: -0.1700
Data Index: 3005697 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19