Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5754. Min Range: -7.5754
Max Act: 7.5754. Min Act: -0.1700
Data Index: 334794 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5754. Min Range: -7.5754
Max Act: 7.0129. Min Act: -0.1700
Data Index: 769203 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.9504. Min Act: -0.1700
Data Index: 4307374 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.9504. Min Act: -0.1700
Data Index: 5852679 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.9192. Min Act: -0.1700
Data Index: 3625512 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 7120282 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.8254. Min Act: -0.1700
Data Index: 5124679 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7629. Min Act: -0.1700
Data Index: 1212600 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7942. Min Act: -0.1700
Data Index: 1700623 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7629. Min Act: -0.1700
Data Index: 8632410 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7629. Min Act: -0.1700
Data Index: 2042972 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7629. Min Act: -0.1700
Data Index: 1212602 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7317. Min Act: -0.1700
Data Index: 7380675 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7629. Min Act: -0.1700
Data Index: 2107593 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7317. Min Act: -0.1700
Data Index: 3714823 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7004. Min Act: -0.1700
Data Index: 3129336 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.7004. Min Act: -0.1700
Data Index: 397790 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.6379. Min Act: -0.1700
Data Index: 202176 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.6692. Min Act: -0.1700
Data Index: 6771702 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5754. Min Range: -7.5754
Max Act: 6.6379. Min Act: -0.1700
Data Index: 1572362 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19