Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4870 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.6353. Min Act: -0.1700
Data Index: 6279631 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.5415. Min Act: -0.1700
Data Index: 7012987 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.5415. Min Act: -0.1700
Data Index: 8340453 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3540. Min Act: -0.1700
Data Index: 5407706 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3540. Min Act: -0.1700
Data Index: 5551512 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3540. Min Act: -0.1700
Data Index: 8507539 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3540. Min Act: -0.1700
Data Index: 2257502 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 6189822 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 8507540 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2915. Min Act: -0.1700
Data Index: 556634 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 4247431 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 5407707 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 17218 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.3228. Min Act: -0.1700
Data Index: 8564073 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2603. Min Act: -0.1700
Data Index: 4247432 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2603. Min Act: -0.1700
Data Index: 3895437 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2603. Min Act: -0.1700
Data Index: 8542211 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2603. Min Act: -0.1700
Data Index: 798807 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2290. Min Act: -0.1700
Data Index: 4749674 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6353. Min Range: -6.6353
Max Act: 6.2290. Min Act: -0.1700
Data Index: 891023 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19