Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1450 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3031. Min Range: -9.3031
Max Act: 9.3031. Min Act: -0.1700
Data Index: 6920516 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3031. Min Range: -9.3031
Max Act: 9.3031. Min Act: -0.1700
Data Index: 8773911 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3031. Min Range: -9.3031
Max Act: 9.1781. Min Act: -0.1700
Data Index: 5554329 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3031. Min Range: -9.3031
Max Act: 9.0531. Min Act: -0.1700
Data Index: 5525874 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3031. Min Range: -9.3031
Max Act: 9.0531. Min Act: -0.1700
Data Index: 5094061 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9906. Min Act: -0.1700
Data Index: 1075740 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9906. Min Act: -0.1700
Data Index: 1634453 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 572271 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 164495 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 7432844 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 1702545 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 8822108 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 6391809 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 4934760 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.8656. Min Act: -0.1700
Data Index: 2195807 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 1944365 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 2251598 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.8656. Min Act: -0.1700
Data Index: 2085953 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.9281. Min Act: -0.1700
Data Index: 1014287 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3031. Min Range: -9.3031
Max Act: 8.8656. Min Act: -0.1700
Data Index: 4975996 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19