Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2852. Min Range: -6.2852
Max Act: 6.2852. Min Act: -0.1700
Data Index: 3312428 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2852. Min Range: -6.2852
Max Act: 6.2540. Min Act: -0.1700
Data Index: 7976365 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2852. Min Range: -6.2852
Max Act: 6.0977. Min Act: -0.1700
Data Index: 802716 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2852. Min Range: -6.2852
Max Act: 6.0665. Min Act: -0.1700
Data Index: 2084789 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.9415. Min Act: -0.1700
Data Index: 5557583 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.9102. Min Act: -0.1700
Data Index: 2052541 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.9102. Min Act: -0.1700
Data Index: 1852956 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8477. Min Act: -0.1700
Data Index: 1412246 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8477. Min Act: -0.1700
Data Index: 1281844 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8477. Min Act: -0.1700
Data Index: 7573986 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8477. Min Act: -0.1700
Data Index: 7568447 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8165. Min Act: -0.1700
Data Index: 7456359 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8165. Min Act: -0.1700
Data Index: 7299258 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8165. Min Act: -0.1700
Data Index: 2507313 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4943396 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8165. Min Act: -0.1700
Data Index: 3254041 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.8165. Min Act: -0.1700
Data Index: 2118524 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.7852. Min Act: -0.1700
Data Index: 6902205 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.7540. Min Act: -0.1700
Data Index: 2801270 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2852. Min Range: -6.2852
Max Act: 5.7540. Min Act: -0.1700
Data Index: 5993760 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19