Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3363. Min Range: -8.3363
Max Act: 8.3363. Min Act: -0.1700
Data Index: 5754823 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3363. Min Range: -8.3363
Max Act: 8.3363. Min Act: -0.1700
Data Index: 765466 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3363. Min Range: -8.3363
Max Act: 8.3363. Min Act: -0.1700
Data Index: 7471292 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3363. Min Range: -8.3363
Max Act: 8.2738. Min Act: -0.1700
Data Index: 4666403 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.9613. Min Act: -0.1700
Data Index: 7435041 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.9613. Min Act: -0.1700
Data Index: 6154671 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.9613. Min Act: -0.1700
Data Index: 7990691 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.8676. Min Act: -0.1700
Data Index: 2610279 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7738. Min Act: -0.1700
Data Index: 5016698 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7426. Min Act: -0.1700
Data Index: 3377752 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7738. Min Act: -0.1700
Data Index: 7724795 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7738. Min Act: -0.1700
Data Index: 5151770 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.8051. Min Act: -0.1700
Data Index: 5705325 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7113. Min Act: -0.1700
Data Index: 8212256 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7426. Min Act: -0.1700
Data Index: 6937233 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.7113. Min Act: -0.1700
Data Index: 4070966 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.6801. Min Act: -0.1700
Data Index: 6179659 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.6801. Min Act: -0.1700
Data Index: 4639568 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.6488. Min Act: -0.1700
Data Index: 193891 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3363. Min Range: -8.3363
Max Act: 7.6488. Min Act: -0.1700
Data Index: 6197963 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19