Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.7870. Min Act: -0.1700
Data Index: 4958092 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.5370. Min Act: -0.1700
Data Index: 2271269 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.5370. Min Act: -0.1700
Data Index: 5468560 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.4120. Min Act: -0.1700
Data Index: 7797401 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.3495. Min Act: -0.1700
Data Index: 7322873 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2870. Min Act: -0.1700
Data Index: 1585601 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2870. Min Act: -0.1700
Data Index: 2764114 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2245. Min Act: -0.1700
Data Index: 6149643 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2870. Min Act: -0.1700
Data Index: 8018915 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2870. Min Act: -0.1700
Data Index: 5232740 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2245. Min Act: -0.1700
Data Index: 2407878 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2245. Min Act: -0.1700
Data Index: 5818231 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.2245. Min Act: -0.1700
Data Index: 2434347 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.1620. Min Act: -0.1700
Data Index: 7196313 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.1620. Min Act: -0.1700
Data Index: 8334088 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.0370. Min Act: -0.1700
Data Index: 3962776 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.0995. Min Act: -0.1700
Data Index: 4855746 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.0995. Min Act: -0.1700
Data Index: 2638235 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.0370. Min Act: -0.1700
Data Index: 3444968 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7870. Min Range: -8.7870
Max Act: 8.0370. Min Act: -0.1700
Data Index: 7736729 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19