Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 709 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.9353. Min Act: -0.1700
Data Index: 5325354 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.8728. Min Act: -0.1700
Data Index: 6655621 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.3728. Min Act: -0.1700
Data Index: 8425186 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.2478. Min Act: -0.1700
Data Index: 4637776 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.1541. Min Act: -0.1700
Data Index: 6057315 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.0291. Min Act: -0.1700
Data Index: 8290101 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9353. Min Range: -8.9353
Max Act: 8.0291. Min Act: -0.1700
Data Index: 5992586 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.9978. Min Act: -0.1700
Data Index: 6859940 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.9353. Min Act: -0.1700
Data Index: 5355146 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 2821662 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 6915732 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.8416. Min Act: -0.1700
Data Index: 8253089 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.8728. Min Act: -0.1700
Data Index: 821859 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.8416. Min Act: -0.1700
Data Index: 839700 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.7791. Min Act: -0.1700
Data Index: 2525685 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.7791. Min Act: -0.1700
Data Index: 8475188 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 1275701 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 6782005 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.7478. Min Act: -0.1700
Data Index: 5542625 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9353. Min Range: -8.9353
Max Act: 7.6853. Min Act: -0.1700
Data Index: 6256460 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19