Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1583. Min Range: -8.1583
Max Act: 8.1583. Min Act: -0.1700
Data Index: 1897949 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.9396. Min Act: -0.1700
Data Index: 6209456 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.7833. Min Act: -0.1700
Data Index: 6902387 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.5646. Min Act: -0.1700
Data Index: 2879547 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.5646. Min Act: -0.1700
Data Index: 7032794 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.5646. Min Act: -0.1700
Data Index: 3751640 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.5021. Min Act: -0.1700
Data Index: 6738162 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.2521. Min Act: -0.1700
Data Index: 4498075 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.2521. Min Act: -0.1700
Data Index: 7952746 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.2208. Min Act: -0.1700
Data Index: 3662029 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1896. Min Act: -0.1700
Data Index: 7925748 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1583. Min Act: -0.1700
Data Index: 6686740 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1896. Min Act: -0.1700
Data Index: 3365323 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1896. Min Act: -0.1700
Data Index: 3732562 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1271. Min Act: -0.1700
Data Index: 7473044 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1271. Min Act: -0.1700
Data Index: 2602133 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1583. Min Act: -0.1700
Data Index: 6771592 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.1271. Min Act: -0.1700
Data Index: 7351496 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.0958. Min Act: -0.1700
Data Index: 2964042 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1583. Min Range: -8.1583
Max Act: 7.0958. Min Act: -0.1700
Data Index: 3956579 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19