Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.8879. Min Act: -0.1700
Data Index: 6221198 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.8566. Min Act: -0.1700
Data Index: 8537536 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.7941. Min Act: -0.1700
Data Index: 1289037 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.7629. Min Act: -0.1700
Data Index: 6250669 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.7004. Min Act: -0.1700
Data Index: 2409931 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.6379. Min Act: -0.1700
Data Index: 3939945 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5754. Min Act: -0.1700
Data Index: 2198796 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5754. Min Act: -0.1700
Data Index: 5912722 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5754. Min Act: -0.1700
Data Index: 8462689 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5441. Min Act: -0.1700
Data Index: 4929962 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5441. Min Act: -0.1700
Data Index: 8186134 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5441. Min Act: -0.1700
Data Index: 6029156 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1965197 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5129. Min Act: -0.1700
Data Index: 4462527 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1327163 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.4816. Min Act: -0.1700
Data Index: 5594272 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.4816. Min Act: -0.1700
Data Index: 5491822 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.4816. Min Act: -0.1700
Data Index: 6984148 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.4816. Min Act: -0.1700
Data Index: 6981676 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8879. Min Range: -6.8879
Max Act: 6.4504. Min Act: -0.1700
Data Index: 4378981 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19