Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2958. Min Range: -10.2958
Max Act: 10.2958. Min Act: -0.1700
Data Index: 548984 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2958. Min Range: -10.2958
Max Act: 10.2333. Min Act: -0.1700
Data Index: 2040230 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2958. Min Range: -10.2958
Max Act: 10.0458. Min Act: -0.1700
Data Index: 7348917 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2958. Min Range: -10.2958
Max Act: 10.0458. Min Act: -0.1700
Data Index: 8774720 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.9833. Min Act: -0.1700
Data Index: 6999452 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2958. Min Range: -10.2958
Max Act: 10.0458. Min Act: -0.1700
Data Index: 3362546 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.9208. Min Act: -0.1700
Data Index: 7094082 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.9208. Min Act: -0.1700
Data Index: 5825427 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.8583. Min Act: -0.1700
Data Index: 6622086 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.7958. Min Act: -0.1700
Data Index: 7010741 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.7958. Min Act: -0.1700
Data Index: 4646638 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.6708. Min Act: -0.1700
Data Index: 7076013 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.6708. Min Act: -0.1700
Data Index: 5425906 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.6083. Min Act: -0.1700
Data Index: 6957386 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.6708. Min Act: -0.1700
Data Index: 719237 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.6083. Min Act: -0.1700
Data Index: 8597529 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.5458. Min Act: -0.1700
Data Index: 400759 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.5458. Min Act: -0.1700
Data Index: 3990983 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.4833. Min Act: -0.1700
Data Index: 4383371 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2958. Min Range: -10.2958
Max Act: 9.4833. Min Act: -0.1700
Data Index: 8120460 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19