Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.7260. Min Act: -0.1700
Data Index: 7109405 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.6010. Min Act: -0.1700
Data Index: 690786 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.5385. Min Act: -0.1700
Data Index: 2637635 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.4135. Min Act: -0.1700
Data Index: 5256187 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.4135. Min Act: -0.1700
Data Index: 4717290 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.2885. Min Act: -0.1700
Data Index: 3654134 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.2885. Min Act: -0.1700
Data Index: 690785 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.2260. Min Act: -0.1700
Data Index: 2637627 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.2260. Min Act: -0.1700
Data Index: 690760 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1635. Min Act: -0.1700
Data Index: 690768 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1635. Min Act: -0.1700
Data Index: 2637618 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1635. Min Act: -0.1700
Data Index: 4607418 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1323. Min Act: -0.1700
Data Index: 690792 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1010. Min Act: -0.1700
Data Index: 2637641 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1010. Min Act: -0.1700
Data Index: 1648443 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1010. Min Act: -0.1700
Data Index: 4220005 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.0385. Min Act: -0.1700
Data Index: 690769 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1010. Min Act: -0.1700
Data Index: 2637648 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.0698. Min Act: -0.1700
Data Index: 2801583 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7260. Min Range: -8.7260
Max Act: 8.1010. Min Act: -0.1700
Data Index: 690767 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19