Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4539 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.5887. Min Act: -0.1700
Data Index: 1675326 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4325. Min Act: -0.1700
Data Index: 6553633 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4637. Min Act: -0.1700
Data Index: 7989953 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4325. Min Act: -0.1700
Data Index: 7403792 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4637. Min Act: -0.1700
Data Index: 4508677 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4637. Min Act: -0.1700
Data Index: 8086749 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4325. Min Act: -0.1700
Data Index: 4342090 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4325. Min Act: -0.1700
Data Index: 5871185 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.4012. Min Act: -0.1700
Data Index: 8672671 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3700. Min Act: -0.1700
Data Index: 5147705 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3700. Min Act: -0.1700
Data Index: 4867303 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3387. Min Act: -0.1700
Data Index: 2671020 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3075. Min Act: -0.1700
Data Index: 2260688 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3075. Min Act: -0.1700
Data Index: 7403773 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3075. Min Act: -0.1700
Data Index: 1254458 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.2762. Min Act: -0.1700
Data Index: 7710459 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.2762. Min Act: -0.1700
Data Index: 5775969 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.3075. Min Act: -0.1700
Data Index: 4227676 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.2762. Min Act: -0.1700
Data Index: 7284246 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5887. Min Range: -6.5887
Max Act: 6.2450. Min Act: -0.1700
Data Index: 7403782 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19