Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 710 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.8601. Min Act: -0.1700
Data Index: 5335697 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.4226. Min Act: -0.1700
Data Index: 4238429 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.4226. Min Act: -0.1700
Data Index: 3393834 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.3601. Min Act: -0.1700
Data Index: 3559537 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.2976. Min Act: -0.1700
Data Index: 7963991 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.1726. Min Act: -0.1700
Data Index: 3629788 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.1101. Min Act: -0.1700
Data Index: 3010497 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.1101. Min Act: -0.1700
Data Index: 8326448 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8601. Min Range: -9.8601
Max Act: 9.0476. Min Act: -0.1700
Data Index: 7431160 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9226. Min Act: -0.1700
Data Index: 6731963 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9851. Min Act: -0.1700
Data Index: 1512542 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9226. Min Act: -0.1700
Data Index: 7261406 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9226. Min Act: -0.1700
Data Index: 8363308 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.8601. Min Act: -0.1700
Data Index: 6795728 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1096075 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.8601. Min Act: -0.1700
Data Index: 6358823 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.9226. Min Act: -0.1700
Data Index: 6421201 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.8601. Min Act: -0.1700
Data Index: 7070299 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.7976. Min Act: -0.1700
Data Index: 8761210 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8601. Min Range: -9.8601
Max Act: 8.6726. Min Act: -0.1700
Data Index: 5120546 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19