Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6358 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0814. Min Range: -8.0814
Max Act: 8.0814. Min Act: -0.1700
Data Index: 6480299 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0814. Min Range: -8.0814
Max Act: 8.0501. Min Act: -0.1700
Data Index: 8789768 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0814. Min Range: -8.0814
Max Act: 8.0814. Min Act: -0.1700
Data Index: 1488907 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0814. Min Range: -8.0814
Max Act: 8.0501. Min Act: -0.1700
Data Index: 7462615 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.9876. Min Act: -0.1700
Data Index: 7462616 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.9564. Min Act: -0.1700
Data Index: 121503 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.9564. Min Act: -0.1700
Data Index: 8445397 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.9251. Min Act: -0.1700
Data Index: 552241 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.9251. Min Act: -0.1700
Data Index: 5998375 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8939. Min Act: -0.1700
Data Index: 6522404 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8314. Min Act: -0.1700
Data Index: 2410362 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8626. Min Act: -0.1700
Data Index: 4521301 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8939. Min Act: -0.1700
Data Index: 4879495 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8314. Min Act: -0.1700
Data Index: 7359238 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8314. Min Act: -0.1700
Data Index: 6433470 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8314. Min Act: -0.1700
Data Index: 7573561 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.8001. Min Act: -0.1700
Data Index: 7859265 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.7689. Min Act: -0.1700
Data Index: 5776383 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.7376. Min Act: -0.1700
Data Index: 1903845 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0814. Min Range: -8.0814
Max Act: 7.7064. Min Act: -0.1700
Data Index: 1870952 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19