Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4371 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.4519. Min Act: -0.1700
Data Index: 5374356 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.3269. Min Act: -0.1700
Data Index: 5780057 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.1394. Min Act: -0.1700
Data Index: 3543944 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1700
Data Index: 463458 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1700
Data Index: 7540853 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1700
Data Index: 3983654 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1700
Data Index: 1788922 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1700
Data Index: 2963037 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0769. Min Act: -0.1699
Data Index: 228872 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0144. Min Act: -0.1700
Data Index: 8579827 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4519. Min Range: -9.4519
Max Act: 9.0144. Min Act: -0.1700
Data Index: 2183519 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 3840591 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 4826974 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8269. Min Act: -0.1700
Data Index: 882946 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 6691841 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 7862403 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 4090731 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8894. Min Act: -0.1700
Data Index: 6256762 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8269. Min Act: -0.1700
Data Index: 6156154 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4519. Min Range: -9.4519
Max Act: 8.8269. Min Act: -0.1700
Data Index: 2046566 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19