Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 927 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0119. Min Range: -5.0119
Max Act: 5.0119. Min Act: -0.1700
Data Index: 2162107 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.7619. Min Act: -0.1700
Data Index: 3124859 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.6369. Min Act: -0.1700
Data Index: 6651432 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.6056. Min Act: -0.1700
Data Index: 19636 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.5744. Min Act: -0.1700
Data Index: 4403988 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.5119. Min Act: -0.1700
Data Index: 6153296 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.5119. Min Act: -0.1700
Data Index: 4699005 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.5119. Min Act: -0.1700
Data Index: 5035796 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.4806. Min Act: -0.1700
Data Index: 531168 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.4806. Min Act: -0.1700
Data Index: 3838658 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.4494. Min Act: -0.1700
Data Index: 1834042 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.4494. Min Act: -0.1700
Data Index: 7573244 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.4181. Min Act: -0.1700
Data Index: 6106556 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3869. Min Act: -0.1700
Data Index: 4553454 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3869. Min Act: -0.1700
Data Index: 4661036 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3244. Min Act: -0.1700
Data Index: 7231492 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3556. Min Act: -0.1700
Data Index: 4837471 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3556. Min Act: -0.1700
Data Index: 4908783 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3556. Min Act: -0.1700
Data Index: 6863752 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0119. Min Range: -5.0119
Max Act: 4.3244. Min Act: -0.1700
Data Index: 7232627 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19