Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.6604. Min Act: -0.1700
Data Index: 6724221 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.4729. Min Act: -0.1700
Data Index: 1807085 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.4104. Min Act: -0.1700
Data Index: 2339907 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.2854. Min Act: -0.1700
Data Index: 6865012 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.2854. Min Act: -0.1700
Data Index: 1225257 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.2541. Min Act: -0.1700
Data Index: 7480715 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.2229. Min Act: -0.1700
Data Index: 5273784 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1916. Min Act: -0.1700
Data Index: 8741951 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1604. Min Act: -0.1700
Data Index: 3444999 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1604. Min Act: -0.1700
Data Index: 3245037 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1291. Min Act: -0.1700
Data Index: 3453528 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1291. Min Act: -0.1700
Data Index: 5431127 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1291. Min Act: -0.1700
Data Index: 1652353 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1291. Min Act: -0.1700
Data Index: 164975 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.1604. Min Act: -0.1700
Data Index: 1966263 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.0979. Min Act: -0.1700
Data Index: 5010832 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.0666. Min Act: -0.1700
Data Index: 4221117 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.0354. Min Act: -0.1700
Data Index: 8098943 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.0666. Min Act: -0.1700
Data Index: 3766128 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6604. Min Range: -6.6604
Max Act: 6.0666. Min Act: -0.1700
Data Index: 1167878 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19