Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.7574. Min Act: -0.1700
Data Index: 8370722 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.4449. Min Act: -0.1700
Data Index: 2343038 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.2574. Min Act: -0.1700
Data Index: 1359128 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.2574. Min Act: -0.1700
Data Index: 74520 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.2574. Min Act: -0.1700
Data Index: 5204693 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.1949. Min Act: -0.1700
Data Index: 6681578 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.1949. Min Act: -0.1700
Data Index: 4584457 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.0699. Min Act: -0.1700
Data Index: 3695712 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7574. Min Range: -9.7574
Max Act: 9.0699. Min Act: -0.1700
Data Index: 8385780 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.9449. Min Act: -0.1700
Data Index: 356786 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.9449. Min Act: -0.1700
Data Index: 4480013 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8824. Min Act: -0.1700
Data Index: 7114697 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8824. Min Act: -0.1700
Data Index: 78829 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8199. Min Act: -0.1700
Data Index: 7018806 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8199. Min Act: -0.1700
Data Index: 5223720 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8824. Min Act: -0.1700
Data Index: 4458371 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8199. Min Act: -0.1700
Data Index: 983375 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8199. Min Act: -0.1700
Data Index: 8491879 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.7574. Min Act: -0.1700
Data Index: 3421066 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7574. Min Range: -9.7574
Max Act: 8.8199. Min Act: -0.1700
Data Index: 893509 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19