Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5258. Min Range: -7.5258
Max Act: 7.5258. Min Act: -0.1700
Data Index: 8695536 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5258. Min Range: -7.5258
Max Act: 7.3383. Min Act: -0.1700
Data Index: 6480290 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5258. Min Range: -7.5258
Max Act: 7.0570. Min Act: -0.1700
Data Index: 1190106 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5258. Min Range: -7.5258
Max Act: 7.0258. Min Act: -0.1700
Data Index: 2778528 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.8695. Min Act: -0.1700
Data Index: 6869108 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.8070. Min Act: -0.1700
Data Index: 7618868 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.7445. Min Act: -0.1700
Data Index: 7026038 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.8070. Min Act: -0.1700
Data Index: 1736617 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.7445. Min Act: -0.1700
Data Index: 8695537 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.7133. Min Act: -0.1700
Data Index: 8695535 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6820. Min Act: -0.1700
Data Index: 8655787 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6820. Min Act: -0.1700
Data Index: 7248170 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6820. Min Act: -0.1700
Data Index: 423157 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6508. Min Act: -0.1700
Data Index: 3555572 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6195. Min Act: -0.1700
Data Index: 1949847 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6195. Min Act: -0.1700
Data Index: 4910071 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6195. Min Act: -0.1700
Data Index: 4064808 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.6195. Min Act: -0.1700
Data Index: 8049617 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.5883. Min Act: -0.1700
Data Index: 6271010 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5258. Min Range: -7.5258
Max Act: 6.5883. Min Act: -0.1700
Data Index: 2596284 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19