Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.4276. Min Act: -0.1700
Data Index: 7684427 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.4276. Min Act: -0.1700
Data Index: 5974820 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.3026. Min Act: -0.1700
Data Index: 5460027 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.3026. Min Act: -0.1700
Data Index: 2799284 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4528801 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0838. Min Act: -0.1700
Data Index: 116266 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0838. Min Act: -0.1700
Data Index: 2631681 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0838. Min Act: -0.1700
Data Index: 4781954 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0838. Min Act: -0.1700
Data Index: 6496114 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0213. Min Act: -0.1700
Data Index: 1515608 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0526. Min Act: -0.1700
Data Index: 2799283 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4276. Min Range: -6.4276
Max Act: 6.0213. Min Act: -0.1700
Data Index: 6104531 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9901. Min Act: -0.1700
Data Index: 8105522 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9901. Min Act: -0.1700
Data Index: 528545 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9588. Min Act: -0.1700
Data Index: 136704 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9588. Min Act: -0.1700
Data Index: 1975820 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9588. Min Act: -0.1700
Data Index: 8691850 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9588. Min Act: -0.1700
Data Index: 6651998 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9276. Min Act: -0.1700
Data Index: 6315081 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4276. Min Range: -6.4276
Max Act: 5.9276. Min Act: -0.1700
Data Index: 4219956 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19