Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6701. Min Range: -7.6701
Max Act: 7.6701. Min Act: -0.1700
Data Index: 3033032 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6701. Min Range: -7.6701
Max Act: 7.3576. Min Act: -0.1700
Data Index: 8370232 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6701. Min Range: -7.6701
Max Act: 7.2639. Min Act: -0.1700
Data Index: 3745554 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6701. Min Range: -7.6701
Max Act: 7.0139. Min Act: -0.1700
Data Index: 5250696 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.7951. Min Act: -0.1700
Data Index: 5275054 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.7639. Min Act: -0.1700
Data Index: 4162255 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.7639. Min Act: -0.1700
Data Index: 5414988 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.7014. Min Act: -0.1700
Data Index: 510450 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6701. Min Act: -0.1700
Data Index: 3552404 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6701. Min Act: -0.1700
Data Index: 1909474 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6389. Min Act: -0.1700
Data Index: 327107 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6389. Min Act: -0.1700
Data Index: 3379294 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6701. Min Act: -0.1700
Data Index: 1913949 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6389. Min Act: -0.1700
Data Index: 5630132 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6076. Min Act: -0.1700
Data Index: 5440926 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6076. Min Act: -0.1700
Data Index: 4527004 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6076. Min Act: -0.1700
Data Index: 3495565 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.6076. Min Act: -0.1700
Data Index: 1568564 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.5764. Min Act: -0.1700
Data Index: 6830112 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6701. Min Range: -7.6701
Max Act: 6.5764. Min Act: -0.1700
Data Index: 5844468 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19