Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2947. Min Act: -0.1700
Data Index: 8466092 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1072. Min Act: -0.1700
Data Index: 3190899 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.9822. Min Act: -0.1700
Data Index: 3136128 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8885. Min Act: -0.1700
Data Index: 5664293 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8572. Min Act: -0.1700
Data Index: 6547152 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8572. Min Act: -0.1700
Data Index: 5346801 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8572. Min Act: -0.1700
Data Index: 1739254 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8260. Min Act: -0.1700
Data Index: 4831845 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.8260. Min Act: -0.1700
Data Index: 6928582 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1501542 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1690760 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7322. Min Act: -0.1700
Data Index: 5300420 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7322. Min Act: -0.1700
Data Index: 5819641 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7010. Min Act: -0.1700
Data Index: 2954704 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7010. Min Act: -0.1700
Data Index: 3524094 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7010. Min Act: -0.1700
Data Index: 4442499 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.7010. Min Act: -0.1700
Data Index: 4796439 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.6697. Min Act: -0.1700
Data Index: 7781065 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.6697. Min Act: -0.1700
Data Index: 4393441 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2947. Min Range: -6.2947
Max Act: 5.6385. Min Act: -0.1700
Data Index: 5838964 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19