Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.8792. Min Act: -0.1700
Data Index: 1720497 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.3480. Min Act: -0.1700
Data Index: 5407061 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.1917. Min Act: -0.1700
Data Index: 3866275 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.1605. Min Act: -0.1700
Data Index: 4126792 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.1292. Min Act: -0.1700
Data Index: 5751785 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0980. Min Act: -0.1700
Data Index: 2384804 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0980. Min Act: -0.1700
Data Index: 6609563 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0667. Min Act: -0.1700
Data Index: 6356320 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0667. Min Act: -0.1700
Data Index: 4947954 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0667. Min Act: -0.1700
Data Index: 5307325 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0667. Min Act: -0.1700
Data Index: 2803711 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0355. Min Act: -0.1700
Data Index: 3717628 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0355. Min Act: -0.1700
Data Index: 2803712 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0042. Min Act: -0.1700
Data Index: 5927778 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0042. Min Act: -0.1700
Data Index: 8176048 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8792. Min Range: -6.8792
Max Act: 6.0042. Min Act: -0.1700
Data Index: 8143226 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8792. Min Range: -6.8792
Max Act: 5.9730. Min Act: -0.1700
Data Index: 8402949 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8792. Min Range: -6.8792
Max Act: 5.9417. Min Act: -0.1700
Data Index: 6291797 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8792. Min Range: -6.8792
Max Act: 5.9417. Min Act: -0.1700
Data Index: 82490 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8792. Min Range: -6.8792
Max Act: 5.9417. Min Act: -0.1700
Data Index: 7135168 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19