Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6050 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.7853. Min Act: -0.1700
Data Index: 4861759 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.7540. Min Act: -0.1700
Data Index: 4606173 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.6602. Min Act: -0.1700
Data Index: 8805650 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.6602. Min Act: -0.1700
Data Index: 7038346 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.6445. Min Act: -0.1700
Data Index: 8164417 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.6289. Min Act: -0.1700
Data Index: 8480485 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5976. Min Act: -0.1700
Data Index: 1814579 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5976. Min Act: -0.1700
Data Index: 7287891 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5819. Min Act: -0.1700
Data Index: 47319 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5663. Min Act: -0.1700
Data Index: 2218161 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5506. Min Act: -0.1700
Data Index: 5016357 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5350. Min Act: -0.1700
Data Index: 6015480 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.5193. Min Act: -0.1700
Data Index: 4539173 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4880. Min Act: -0.1700
Data Index: 3967498 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4723. Min Act: -0.1700
Data Index: 3118897 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4723. Min Act: -0.1700
Data Index: 4123714 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4566. Min Act: -0.1700
Data Index: 3386721 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4566. Min Act: -0.1700
Data Index: 2182168 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4410. Min Act: -0.1700
Data Index: 4370756 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7853. Min Range: -3.7853
Max Act: 3.4410. Min Act: -0.1700
Data Index: 8330306 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19