Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.2311. Min Act: -0.1700
Data Index: 8805023 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.2311. Min Act: -0.1700
Data Index: 5914619 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.1999. Min Act: -0.1700
Data Index: 6691881 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.1686. Min Act: -0.1700
Data Index: 2279397 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.1061. Min Act: -0.1700
Data Index: 5296123 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0749. Min Act: -0.1700
Data Index: 4581807 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0436. Min Act: -0.1700
Data Index: 4061206 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0436. Min Act: -0.1700
Data Index: 198742 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 834519 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 7574412 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 2520902 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 2780543 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 1535982 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2311. Min Range: -5.2311
Max Act: 5.0124. Min Act: -0.1700
Data Index: 1633859 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9811. Min Act: -0.1700
Data Index: 2379322 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9811. Min Act: -0.1700
Data Index: 3241157 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9811. Min Act: -0.1700
Data Index: 1074528 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9499. Min Act: -0.1700
Data Index: 4533326 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9811. Min Act: -0.1700
Data Index: 2261482 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2311. Min Range: -5.2311
Max Act: 4.9811. Min Act: -0.1700
Data Index: 7151737 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19