Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1705 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.8535. Min Act: -0.1700
Data Index: 3655110 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.7285. Min Act: -0.1700
Data Index: 2687264 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.4785. Min Act: -0.1700
Data Index: 1463885 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.4160. Min Act: -0.1700
Data Index: 1837934 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.3535. Min Act: -0.1700
Data Index: 8250608 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.3535. Min Act: -0.1700
Data Index: 4856867 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2910. Min Act: -0.1700
Data Index: 6291269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2910. Min Act: -0.1700
Data Index: 464260 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.3535. Min Act: -0.1700
Data Index: 5580879 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2910. Min Act: -0.1700
Data Index: 7135673 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2910. Min Act: -0.1700
Data Index: 7262646 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2910. Min Act: -0.1700
Data Index: 7343084 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2285. Min Act: -0.1700
Data Index: 5177829 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.1035. Min Act: -0.1700
Data Index: 4336802 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.1660. Min Act: -0.1700
Data Index: 3172624 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.1660. Min Act: -0.1700
Data Index: 1936203 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.1660. Min Act: -0.1700
Data Index: 5494053 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.2285. Min Act: -0.1700
Data Index: 5327006 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.0410. Min Act: -0.1700
Data Index: 7338221 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8535. Min Range: -8.8535
Max Act: 8.0410. Min Act: -0.1700
Data Index: 5610372 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19