Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.4875. Min Act: -0.1700
Data Index: 33755 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.3000. Min Act: -0.1700
Data Index: 6170078 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.2375. Min Act: -0.1700
Data Index: 6097651 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.1125. Min Act: -0.1700
Data Index: 5797593 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.1125. Min Act: -0.1700
Data Index: 4214798 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.0500. Min Act: -0.1700
Data Index: 7226970 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.0500. Min Act: -0.1700
Data Index: 4162609 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9875. Min Act: -0.1700
Data Index: 8068540 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.0500. Min Act: -0.1700
Data Index: 228250 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9875. Min Act: -0.1700
Data Index: 152027 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9875. Min Act: -0.1700
Data Index: 8162801 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4875. Min Range: -8.4875
Max Act: 8.0500. Min Act: -0.1700
Data Index: 2356554 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9250. Min Act: -0.1700
Data Index: 7698083 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9250. Min Act: -0.1700
Data Index: 4176979 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.9250. Min Act: -0.1700
Data Index: 6798493 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.8625. Min Act: -0.1700
Data Index: 5678267 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.8625. Min Act: -0.1700
Data Index: 3035459 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.8625. Min Act: -0.1700
Data Index: 6140015 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.8625. Min Act: -0.1700
Data Index: 2993574 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4875. Min Range: -8.4875
Max Act: 7.8625. Min Act: -0.1700
Data Index: 6590626 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19