Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.6353. Min Act: -0.1700
Data Index: 3266364 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.4790. Min Act: -0.1700
Data Index: 5220739 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.3853. Min Act: -0.1700
Data Index: 6457350 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.2290. Min Act: -0.1700
Data Index: 5791019 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.1978. Min Act: -0.1700
Data Index: 3604088 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.1040. Min Act: -0.1700
Data Index: 4663816 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.1353. Min Act: -0.1700
Data Index: 590673 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.0103. Min Act: -0.1700
Data Index: 351406 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.0415. Min Act: -0.1700
Data Index: 1367631 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.0415. Min Act: -0.1700
Data Index: 7909633 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.0103. Min Act: -0.1700
Data Index: 5596631 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6353. Min Range: -7.6353
Max Act: 7.0103. Min Act: -0.1700
Data Index: 1007749 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9790. Min Act: -0.1700
Data Index: 4075919 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9790. Min Act: -0.1700
Data Index: 7404418 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9790. Min Act: -0.1700
Data Index: 6039291 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9478. Min Act: -0.1700
Data Index: 8096173 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9790. Min Act: -0.1700
Data Index: 2941591 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.9478. Min Act: -0.1700
Data Index: 7350314 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.8853. Min Act: -0.1700
Data Index: 4089376 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6353. Min Range: -7.6353
Max Act: 6.8853. Min Act: -0.1700
Data Index: 7794382 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19