Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6138 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0754. Min Range: -8.0754
Max Act: 8.0754. Min Act: -0.1700
Data Index: 2268680 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.9504. Min Act: -0.1700
Data Index: 2555471 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.8879. Min Act: -0.1700
Data Index: 2905312 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.7629. Min Act: -0.1700
Data Index: 6899086 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.5754. Min Act: -0.1700
Data Index: 1913093 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.5129. Min Act: -0.1700
Data Index: 4479923 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.4504. Min Act: -0.1700
Data Index: 3711193 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.4504. Min Act: -0.1700
Data Index: 1864750 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.4192. Min Act: -0.1700
Data Index: 3183798 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.3567. Min Act: -0.1700
Data Index: 617985 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.3567. Min Act: -0.1700
Data Index: 1408182 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.3879. Min Act: -0.1700
Data Index: 6045564 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.3254. Min Act: -0.1700
Data Index: 69986 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.3254. Min Act: -0.1700
Data Index: 2107275 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2942. Min Act: -0.1700
Data Index: 5311168 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2317. Min Act: -0.1700
Data Index: 4982695 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2317. Min Act: -0.1700
Data Index: 4779770 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2317. Min Act: -0.1700
Data Index: 3607343 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2317. Min Act: -0.1700
Data Index: 1928327 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0754. Min Range: -8.0754
Max Act: 7.2004. Min Act: -0.1700
Data Index: 6663911 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19