Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.4108. Min Act: -0.1700
Data Index: 312315 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.2858. Min Act: -0.1700
Data Index: 6306674 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.2858. Min Act: -0.1700
Data Index: 6495932 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.2858. Min Act: -0.1700
Data Index: 3673870 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 735250 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 1460161 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 126796 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.0358. Min Act: -0.1700
Data Index: 125388 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 1378751 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 1148734 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 1115536 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 1100506 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 344194 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.0358. Min Act: -0.1700
Data Index: 76796 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 952145 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 293418 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 849855 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 786164 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.2858. Min Act: -0.1700
Data Index: 717214 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.4108. Min Range: -21.4108
Max Act: 21.1608. Min Act: -0.1700
Data Index: 652655 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19