Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1651. Min Range: -8.1651
Max Act: 8.1651. Min Act: -0.1700
Data Index: 4435378 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1651. Min Range: -8.1651
Max Act: 8.0401. Min Act: -0.1700
Data Index: 6770984 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.9151. Min Act: -0.1700
Data Index: 1482310 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.8526. Min Act: -0.1700
Data Index: 4496285 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.7901. Min Act: -0.1700
Data Index: 3863517 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.7901. Min Act: -0.1700
Data Index: 7535042 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.7276. Min Act: -0.1700
Data Index: 6632873 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.6651. Min Act: -0.1700
Data Index: 1010769 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.6651. Min Act: -0.1700
Data Index: 550720 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.6651. Min Act: -0.1700
Data Index: 6934795 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.6651. Min Act: -0.1700
Data Index: 5606691 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.6026. Min Act: -0.1700
Data Index: 1997344 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.5401. Min Act: -0.1700
Data Index: 8561109 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.5401. Min Act: -0.1700
Data Index: 5021404 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.5401. Min Act: -0.1700
Data Index: 2533066 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.4776. Min Act: -0.1700
Data Index: 1349795 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.4151. Min Act: -0.1700
Data Index: 5455216 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.4151. Min Act: -0.1700
Data Index: 2858798 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.4151. Min Act: -0.1700
Data Index: 295537 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1651. Min Range: -8.1651
Max Act: 7.4151. Min Act: -0.1700
Data Index: 563105 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19