Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.2415. Min Act: -0.1700
Data Index: 7697808 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.3040. Min Act: -0.1700
Data Index: 1673024 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.0853. Min Act: -0.1700
Data Index: 5555419 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.0853. Min Act: -0.1700
Data Index: 2458548 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.0853. Min Act: -0.1700
Data Index: 2870166 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.0853. Min Act: -0.1700
Data Index: 7948491 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3040. Min Range: -8.3040
Max Act: 8.0540. Min Act: -0.1700
Data Index: 4541792 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.9915. Min Act: -0.1700
Data Index: 3581599 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.9603. Min Act: -0.1700
Data Index: 1735579 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.9290. Min Act: -0.1700
Data Index: 3010888 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.9290. Min Act: -0.1700
Data Index: 4723592 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.8353. Min Act: -0.1700
Data Index: 7229607 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.8353. Min Act: -0.1700
Data Index: 1402374 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.8040. Min Act: -0.1700
Data Index: 7059284 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.8040. Min Act: -0.1700
Data Index: 5700920 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.7728. Min Act: -0.1700
Data Index: 160525 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.7415. Min Act: -0.1700
Data Index: 7062626 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.7728. Min Act: -0.1700
Data Index: 2227699 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.8040. Min Act: -0.1700
Data Index: 4492116 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3040. Min Range: -8.3040
Max Act: 7.7728. Min Act: -0.1700
Data Index: 2299308 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19