Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5098 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.6000. Min Act: -0.1700
Data Index: 3677209 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.3813. Min Act: -0.1700
Data Index: 3791130 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6000. Min Range: -7.6000
Max Act: 7.3813. Min Act: -0.1700
Data Index: 210324 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.9125. Min Act: -0.1700
Data Index: 139234 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7875. Min Act: -0.1700
Data Index: 5555773 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7875. Min Act: -0.1700
Data Index: 3154309 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7563. Min Act: -0.1700
Data Index: 57503 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7250. Min Act: -0.1700
Data Index: 3560287 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7250. Min Act: -0.1700
Data Index: 3830855 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.7250. Min Act: -0.1700
Data Index: 6979695 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6938. Min Act: -0.1700
Data Index: 6282409 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6938. Min Act: -0.1700
Data Index: 1366333 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6625. Min Act: -0.1700
Data Index: 6562291 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6625. Min Act: -0.1700
Data Index: 8176562 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6625. Min Act: -0.1700
Data Index: 4290975 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6625. Min Act: -0.1700
Data Index: 1005022 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6313. Min Act: -0.1700
Data Index: 1415672 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6000. Min Act: -0.1700
Data Index: 6553533 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.6000. Min Act: -0.1700
Data Index: 5687964 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6000. Min Range: -7.6000
Max Act: 6.5688. Min Act: -0.1700
Data Index: 3719535 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19