Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.9208. Min Act: -0.1700
Data Index: 5920394 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.8583. Min Act: -0.1700
Data Index: 6075014 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.8583. Min Act: -0.1700
Data Index: 6856398 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.8583. Min Act: -0.1700
Data Index: 6578443 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7958. Min Act: -0.1700
Data Index: 2157384 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7958. Min Act: -0.1700
Data Index: 3495222 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7646. Min Act: -0.1700
Data Index: 5949597 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7646. Min Act: -0.1700
Data Index: 684458 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7021. Min Act: -0.1700
Data Index: 1866297 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.7021. Min Act: -0.1700
Data Index: 8822112 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6708. Min Act: -0.1700
Data Index: 1518274 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6708. Min Act: -0.1700
Data Index: 3233697 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6396. Min Act: -0.1700
Data Index: 4559851 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6396. Min Act: -0.1700
Data Index: 2029795 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6396. Min Act: -0.1700
Data Index: 2540142 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6396. Min Act: -0.1700
Data Index: 4025145 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6396. Min Act: -0.1700
Data Index: 1768094 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.6083. Min Act: -0.1700
Data Index: 3520538 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.5771. Min Act: -0.1700
Data Index: 3775193 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9208. Min Range: -6.9208
Max Act: 6.5771. Min Act: -0.1700
Data Index: 3800088 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19