Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3661 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.9357. Min Act: -0.1700
Data Index: 8683586 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.9044. Min Act: -0.1700
Data Index: 3333718 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 284325 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 6203542 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 432569 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8732. Min Act: -0.1700
Data Index: 8010328 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 6349678 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 224830 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 7003667 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8419. Min Act: -0.1700
Data Index: 5393564 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 8464047 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5722193 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5652337 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 7628617 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 7068905 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.8107. Min Act: -0.1700
Data Index: 1612831 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.7794. Min Act: -0.1700
Data Index: 4664756 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.7794. Min Act: -0.1700
Data Index: 4841574 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.7482. Min Act: -0.1700
Data Index: 4944570 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9357. Min Range: -4.9357
Max Act: 4.7482. Min Act: -0.1700
Data Index: 3941135 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19