Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.4731. Min Act: -0.1700
Data Index: 4131551 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.4574. Min Act: -0.1700
Data Index: 676994 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3791. Min Act: -0.1700
Data Index: 8518813 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3634. Min Act: -0.1700
Data Index: 8470004 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3320. Min Act: -0.1700
Data Index: 676993 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3320. Min Act: -0.1700
Data Index: 3939742 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3006. Min Act: -0.1700
Data Index: 1185 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2849. Min Act: -0.1700
Data Index: 28572 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2849. Min Act: -0.1700
Data Index: 4339771 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.3006. Min Act: -0.1700
Data Index: 2431981 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2849. Min Act: -0.1700
Data Index: 561895 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2849. Min Act: -0.1700
Data Index: 2178012 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2849. Min Act: -0.1700
Data Index: 8016892 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2692. Min Act: -0.1700
Data Index: 7312393 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2692. Min Act: -0.1700
Data Index: 8330670 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2535. Min Act: -0.1700
Data Index: 5795797 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2535. Min Act: -0.1700
Data Index: 6128784 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2535. Min Act: -0.1700
Data Index: 3477248 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2535. Min Act: -0.1700
Data Index: 1100160 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4731. Min Range: -3.4731
Max Act: 3.2221. Min Act: -0.1700
Data Index: 8444025 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19