Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1026. Min Range: -9.1026
Max Act: 9.1026. Min Act: -0.1700
Data Index: 3490677 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1026. Min Range: -9.1026
Max Act: 9.0401. Min Act: -0.1700
Data Index: 2445862 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.9776. Min Act: -0.1700
Data Index: 2445856 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.9151. Min Act: -0.1700
Data Index: 3624756 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.9151. Min Act: -0.1700
Data Index: 2445858 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.9151. Min Act: -0.1700
Data Index: 2445864 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.9151. Min Act: -0.1700
Data Index: 6690209 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.8526. Min Act: -0.1700
Data Index: 2445857 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.7901. Min Act: -0.1700
Data Index: 8211381 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.7901. Min Act: -0.1700
Data Index: 3542472 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.7276. Min Act: -0.1700
Data Index: 1486168 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.7901. Min Act: -0.1700
Data Index: 498433 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.7276. Min Act: -0.1700
Data Index: 6004304 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6651. Min Act: -0.1700
Data Index: 2445867 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6026. Min Act: -0.1700
Data Index: 5609097 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.5401. Min Act: -0.1700
Data Index: 1209992 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6026. Min Act: -0.1700
Data Index: 4831840 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6026. Min Act: -0.1700
Data Index: 5308472 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6026. Min Act: -0.1700
Data Index: 1502209 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1026. Min Range: -9.1026
Max Act: 8.6026. Min Act: -0.1700
Data Index: 4188294 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19