Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2343 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3896. Min Act: -0.1700
Data Index: 3865440 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3271. Min Act: -0.1700
Data Index: 4398788 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.3271. Min Act: -0.1700
Data Index: 6175024 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.2646. Min Act: -0.1700
Data Index: 1205434 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0771. Min Act: -0.1700
Data Index: 7289673 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0771. Min Act: -0.1700
Data Index: 7871576 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0771. Min Act: -0.1700
Data Index: 1443545 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3896. Min Range: -8.3896
Max Act: 8.0771. Min Act: -0.1700
Data Index: 8100015 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.9521. Min Act: -0.1700
Data Index: 28131 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.8271. Min Act: -0.1700
Data Index: 4150919 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.8271. Min Act: -0.1700
Data Index: 1730478 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.8271. Min Act: -0.1700
Data Index: 7717943 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.8271. Min Act: -0.1700
Data Index: 5115475 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7646. Min Act: -0.1700
Data Index: 6496043 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7646. Min Act: -0.1700
Data Index: 7042014 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7646. Min Act: -0.1700
Data Index: 2165965 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7021. Min Act: -0.1700
Data Index: 277374 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7021. Min Act: -0.1700
Data Index: 5242671 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7021. Min Act: -0.1700
Data Index: 7862987 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3896. Min Range: -8.3896
Max Act: 7.7021. Min Act: -0.1700
Data Index: 3576773 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19