Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3592. Min Range: -6.3592
Max Act: 6.3592. Min Act: -0.1700
Data Index: 8430133 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3592. Min Range: -6.3592
Max Act: 6.2342. Min Act: -0.1700
Data Index: 6885247 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3592. Min Range: -6.3592
Max Act: 6.1404. Min Act: -0.1700
Data Index: 2049751 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.9842. Min Act: -0.1700
Data Index: 5700060 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.8904. Min Act: -0.1700
Data Index: 6824673 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.7654. Min Act: -0.1700
Data Index: 4789393 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6717. Min Act: -0.1700
Data Index: 2207703 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6717. Min Act: -0.1700
Data Index: 2481704 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6717. Min Act: -0.1700
Data Index: 6849537 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 2463062 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 8027647 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 5930366 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5779. Min Act: -0.1700
Data Index: 315827 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5779. Min Act: -0.1700
Data Index: 6985563 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5779. Min Act: -0.1700
Data Index: 4913556 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5467. Min Act: -0.1700
Data Index: 2003636 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5779. Min Act: -0.1700
Data Index: 8480152 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5467. Min Act: -0.1700
Data Index: 2879974 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5154. Min Act: -0.1700
Data Index: 6873104 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3592. Min Range: -6.3592
Max Act: 5.5154. Min Act: -0.1700
Data Index: 7441690 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19