Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.9014. Min Act: -0.1700
Data Index: 3135388 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.9014. Min Act: -0.1700
Data Index: 294707 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.7139. Min Act: -0.1696
Data Index: 1111921 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.5264. Min Act: -0.1700
Data Index: 5656044 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.4639. Min Act: -0.1700
Data Index: 1249180 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.4639. Min Act: -0.1700
Data Index: 218678 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.3389. Min Act: -0.1700
Data Index: 2775735 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.3389. Min Act: -0.1700
Data Index: 2480451 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.3389. Min Act: -0.1700
Data Index: 6393275 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.3076. Min Act: -0.1700
Data Index: 1277182 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.2764. Min Act: -0.1698
Data Index: 1621627 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 6427592 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.1201. Min Act: -0.1697
Data Index: 1887850 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 6131514 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.0889. Min Act: -0.1700
Data Index: 4272372 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.0889. Min Act: -0.1700
Data Index: 5943304 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.1514. Min Act: -0.1700
Data Index: 651507 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.0576. Min Act: -0.1700
Data Index: 454323 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.0576. Min Act: -0.1700
Data Index: 1169860 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9014. Min Range: -7.9014
Max Act: 7.0576. Min Act: -0.1700
Data Index: 6029967 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19