Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.3561. Min Act: -0.1700
Data Index: 1458782 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.2624. Min Act: -0.1700
Data Index: 3422448 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.2936. Min Act: -0.1700
Data Index: 7801707 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.2936. Min Act: -0.1700
Data Index: 7409006 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1999. Min Act: -0.1700
Data Index: 8624419 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1999. Min Act: -0.1700
Data Index: 6805717 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1686. Min Act: -0.1700
Data Index: 678882 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1999. Min Act: -0.1700
Data Index: 3069411 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1374. Min Act: -0.1700
Data Index: 1145088 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.1061. Min Act: -0.1700
Data Index: 5125741 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.0749. Min Act: -0.1700
Data Index: 5602732 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3561. Min Range: -8.3561
Max Act: 8.0749. Min Act: -0.1700
Data Index: 6613600 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.9811. Min Act: -0.1700
Data Index: 907065 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.9186. Min Act: -0.1700
Data Index: 3065963 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.8561. Min Act: -0.1700
Data Index: 2307591 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8425442 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.6999. Min Act: -0.1700
Data Index: 413119 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.6061. Min Act: -0.1700
Data Index: 6400858 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.4811. Min Act: -0.1700
Data Index: 954985 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3561. Min Range: -8.3561
Max Act: 7.4186. Min Act: -0.1700
Data Index: 525963 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19