Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4773 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.5952. Min Range: -18.5952
Max Act: 18.5952. Min Act: -0.1700
Data Index: 5804761 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.5952. Min Range: -18.5952
Max Act: 17.3452. Min Act: -0.1700
Data Index: 6267637 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.5952. Min Range: -18.5952
Max Act: 17.2202. Min Act: -0.1700
Data Index: 6588749 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.5952. Min Range: -18.5952
Max Act: 17.2202. Min Act: -0.1700
Data Index: 7835559 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.5952. Min Range: -18.5952
Max Act: 17.0952. Min Act: -0.1700
Data Index: 2858524 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.5952. Min Range: -18.5952
Max Act: 17.0952. Min Act: -0.1700
Data Index: 2655328 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 4950894 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.9702. Min Act: -0.1700
Data Index: 5538436 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.9702. Min Act: -0.1700
Data Index: 5286564 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 7083131 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 3004224 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 4136619 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 7887316 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 3327562 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.8452. Min Act: -0.1700
Data Index: 5343884 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.7202. Min Act: -0.1700
Data Index: 7407469 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.7202. Min Act: -0.1700
Data Index: 7419769 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.7202. Min Act: -0.1700
Data Index: 136162 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.7202. Min Act: -0.1700
Data Index: 3004221 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.5952. Min Range: -18.5952
Max Act: 16.5952. Min Act: -0.1700
Data Index: 2052073 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19