Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1590. Min Range: -12.1590
Max Act: 12.1590. Min Act: -0.1700
Data Index: 354557 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1590. Min Range: -12.1590
Max Act: 12.0965. Min Act: -0.1700
Data Index: 770491 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1590. Min Range: -12.1590
Max Act: 12.0340. Min Act: -0.1700
Data Index: 1891113 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.9715. Min Act: -0.1700
Data Index: 4980930 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.9715. Min Act: -0.1700
Data Index: 1244787 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.9090. Min Act: -0.1700
Data Index: 1296447 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.8465. Min Act: -0.1700
Data Index: 6363641 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.8465. Min Act: -0.1700
Data Index: 1204705 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.8465. Min Act: -0.1700
Data Index: 3214105 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.8465. Min Act: -0.1700
Data Index: 637401 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7840. Min Act: -0.1700
Data Index: 2068218 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7840. Min Act: -0.1700
Data Index: 6472608 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 1173658 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 8115413 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 6742812 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 7753330 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 7724724 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 4340236 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 7077171 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1590. Min Range: -12.1590
Max Act: 11.7215. Min Act: -0.1700
Data Index: 5453355 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19