Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.3873. Min Act: -0.1700
Data Index: 8277928 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.3873. Min Act: -0.1700
Data Index: 8401250 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.3561. Min Act: -0.1700
Data Index: 7221100 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.2311. Min Act: -0.1700
Data Index: 506713 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1998. Min Act: -0.1700
Data Index: 5509339 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1373. Min Act: -0.1700
Data Index: 8618719 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1061. Min Act: -0.1700
Data Index: 4372230 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1061. Min Act: -0.1700
Data Index: 4383771 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1061. Min Act: -0.1700
Data Index: 6636573 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.0748. Min Act: -0.1700
Data Index: 5600745 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.0436. Min Act: -0.1700
Data Index: 8053491 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.0123. Min Act: -0.1700
Data Index: 1370288 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9811. Min Act: -0.1700
Data Index: 5077913 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9498. Min Act: -0.1700
Data Index: 1556036 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9498. Min Act: -0.1700
Data Index: 531376 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9811. Min Act: -0.1700
Data Index: 7204507 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9811. Min Act: -0.1700
Data Index: 8627110 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9498. Min Act: -0.1700
Data Index: 5901001 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9498. Min Act: -0.1700
Data Index: 4813457 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9186. Min Act: -0.1700
Data Index: 757937 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19