Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.1642. Min Act: -0.1700
Data Index: 7092468 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.1017. Min Act: -0.1700
Data Index: 8731836 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.1017. Min Act: -0.1700
Data Index: 6377080 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.0704. Min Act: -0.1700
Data Index: 4363008 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.0079. Min Act: -0.1700
Data Index: 5848542 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.0704. Min Act: -0.1700
Data Index: 3512772 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.9767. Min Act: -0.1700
Data Index: 4253134 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.0079. Min Act: -0.1700
Data Index: 5098974 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1642. Min Range: -8.1642
Max Act: 8.0392. Min Act: -0.1700
Data Index: 4400720 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.9454. Min Act: -0.1700
Data Index: 6738730 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.9454. Min Act: -0.1700
Data Index: 2505706 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8517. Min Act: -0.1700
Data Index: 7910748 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8517. Min Act: -0.1700
Data Index: 5747515 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8517. Min Act: -0.1700
Data Index: 6471710 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8517. Min Act: -0.1700
Data Index: 6143571 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8517. Min Act: -0.1700
Data Index: 1236964 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8204. Min Act: -0.1700
Data Index: 5011720 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8204. Min Act: -0.1700
Data Index: 5158420 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.8204. Min Act: -0.1700
Data Index: 541480 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1642. Min Range: -8.1642
Max Act: 7.7892. Min Act: -0.1700
Data Index: 2919736 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19