Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3987 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.3471. Min Act: -0.1700
Data Index: 1287462 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.3471. Min Act: -0.1700
Data Index: 3519581 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.3159. Min Act: -0.1700
Data Index: 462752 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.1909. Min Act: -0.1700
Data Index: 1006258 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.1596. Min Act: -0.1700
Data Index: 6371745 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.0971. Min Act: -0.1700
Data Index: 925527 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.0971. Min Act: -0.1700
Data Index: 2578065 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.0971. Min Act: -0.1700
Data Index: 6177159 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.0659. Min Act: -0.1700
Data Index: 5048135 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3471. Min Range: -7.3471
Max Act: 7.0346. Min Act: -0.1700
Data Index: 4025145 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9721. Min Act: -0.1700
Data Index: 6780121 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9721. Min Act: -0.1700
Data Index: 7408155 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9721. Min Act: -0.1700
Data Index: 1472644 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9409. Min Act: -0.1700
Data Index: 4999586 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9409. Min Act: -0.1700
Data Index: 4712096 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9096. Min Act: -0.1700
Data Index: 4888631 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.9096. Min Act: -0.1700
Data Index: 623538 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.8784. Min Act: -0.1700
Data Index: 3973775 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.8784. Min Act: -0.1700
Data Index: 3840951 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3471. Min Range: -7.3471
Max Act: 6.8784. Min Act: -0.1700
Data Index: 2452670 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19