Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.2998. Min Act: -0.1700
Data Index: 1458818 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.2686. Min Act: -0.1700
Data Index: 3817507 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.2373. Min Act: -0.1700
Data Index: 1236008 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.1748. Min Act: -0.1700
Data Index: 2662371 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.2061. Min Act: -0.1700
Data Index: 3367154 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.1748. Min Act: -0.1700
Data Index: 6559432 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.1436. Min Act: -0.1700
Data Index: 7200754 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.1436. Min Act: -0.1700
Data Index: 4994916 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.0811. Min Act: -0.1700
Data Index: 7732688 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2998. Min Range: -7.2998
Max Act: 7.0498. Min Act: -0.1700
Data Index: 7416596 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9873. Min Act: -0.1700
Data Index: 428316 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9873. Min Act: -0.1700
Data Index: 7805646 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9873. Min Act: -0.1700
Data Index: 4833864 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9248. Min Act: -0.1700
Data Index: 8701287 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9561. Min Act: -0.1700
Data Index: 918104 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9248. Min Act: -0.1700
Data Index: 5947453 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9248. Min Act: -0.1700
Data Index: 3523565 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.9248. Min Act: -0.1700
Data Index: 7349768 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.8936. Min Act: -0.1700
Data Index: 3812617 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2998. Min Range: -7.2998
Max Act: 6.8623. Min Act: -0.1700
Data Index: 6189851 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19