Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 609 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6993. Min Act: -0.1700
Data Index: 5140416 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 7034261 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 5794831 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6680. Min Act: -0.1700
Data Index: 5879822 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.6368. Min Act: -0.1700
Data Index: 2338227 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5118. Min Act: -0.1700
Data Index: 5714441 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.5118. Min Act: -0.1700
Data Index: 5542945 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4805. Min Act: -0.1700
Data Index: 5898922 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4805. Min Act: -0.1700
Data Index: 8711876 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4805. Min Act: -0.1700
Data Index: 8350569 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4493. Min Act: -0.1700
Data Index: 6187580 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4493. Min Act: -0.1700
Data Index: 1685257 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4493. Min Act: -0.1700
Data Index: 3616543 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 3387017 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5156969 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 3319646 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 2764916 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 7926853 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 7691062 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6993. Min Range: -4.6993
Max Act: 4.4180. Min Act: -0.1700
Data Index: 8430025 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19