Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0559. Min Range: -7.0559
Max Act: 7.0559. Min Act: -0.1700
Data Index: 480041 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8997. Min Act: -0.1700
Data Index: 3352236 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8684. Min Act: -0.1700
Data Index: 703247 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8684. Min Act: -0.1700
Data Index: 2011683 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8372. Min Act: -0.1700
Data Index: 7854560 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8059. Min Act: -0.1700
Data Index: 1199084 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7747. Min Act: -0.1700
Data Index: 3460158 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8059. Min Act: -0.1700
Data Index: 5363100 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.8059. Min Act: -0.1700
Data Index: 848446 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7434. Min Act: -0.1700
Data Index: 5285414 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7122. Min Act: -0.1700
Data Index: 6444676 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7122. Min Act: -0.1700
Data Index: 4109516 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7122. Min Act: -0.1700
Data Index: 5345028 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.7122. Min Act: -0.1700
Data Index: 1940901 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6809. Min Act: -0.1700
Data Index: 1725953 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6809. Min Act: -0.1700
Data Index: 836790 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6497. Min Act: -0.1700
Data Index: 69195 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6497. Min Act: -0.1700
Data Index: 6204855 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6497. Min Act: -0.1700
Data Index: 6766430 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0559. Min Range: -7.0559
Max Act: 6.6184. Min Act: -0.1700
Data Index: 4396055 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19