Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6324 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.6623. Min Act: -0.1700
Data Index: 6666928 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.6623. Min Act: -0.1700
Data Index: 5715632 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.6310. Min Act: -0.1700
Data Index: 5291679 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.6310. Min Act: -0.1700
Data Index: 8268012 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.5998. Min Act: -0.1700
Data Index: 7835609 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.5373. Min Act: -0.1700
Data Index: 6218835 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.5373. Min Act: -0.1700
Data Index: 1786760 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.5060. Min Act: -0.1700
Data Index: 709803 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4748. Min Act: -0.1700
Data Index: 5443799 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4748. Min Act: -0.1700
Data Index: 2304429 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4748. Min Act: -0.1700
Data Index: 3536854 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4435. Min Act: -0.1700
Data Index: 117709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4748. Min Act: -0.1700
Data Index: 1941759 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4435. Min Act: -0.1700
Data Index: 2660610 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.3810. Min Act: -0.1700
Data Index: 2205322 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4123. Min Act: -0.1700
Data Index: 2486235 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4123. Min Act: -0.1700
Data Index: 4717033 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4123. Min Act: -0.1700
Data Index: 7726897 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4435. Min Act: -0.1700
Data Index: 1449044 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6623. Min Range: -5.6623
Max Act: 5.4123. Min Act: -0.1700
Data Index: 2257532 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19