Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.7200. Min Act: -0.1700
Data Index: 799247 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.7200. Min Act: -0.1700
Data Index: 405436 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.7200. Min Act: -0.1698
Data Index: 5992899 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6887. Min Act: -0.1700
Data Index: 3899425 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6887. Min Act: -0.1700
Data Index: 5080085 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6887. Min Act: -0.1700
Data Index: 3439977 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6887. Min Act: -0.1700
Data Index: 3289763 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6887. Min Act: -0.1700
Data Index: 7436225 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 2754092 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 8682631 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 1339884 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 4799458 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 7397841 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6262. Min Act: -0.1700
Data Index: 1427785 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.5950. Min Act: -0.1700
Data Index: 3440749 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 8054545 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6575. Min Act: -0.1700
Data Index: 8180788 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6262. Min Act: -0.1700
Data Index: 3640793 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6262. Min Act: -0.1700
Data Index: 2560516 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7200. Min Range: -4.7200
Max Act: 4.6262. Min Act: -0.1700
Data Index: 6716369 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19