Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.3393. Min Act: -0.1700
Data Index: 5415043 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.3393. Min Act: -0.1700
Data Index: 1171057 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.3393. Min Act: -0.1700
Data Index: 2054776 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.3393. Min Act: -0.1700
Data Index: 7700297 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.3080. Min Act: -0.1700
Data Index: 2295632 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.2768. Min Act: -0.1700
Data Index: 3418639 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.2768. Min Act: -0.1700
Data Index: 6304146 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.2455. Min Act: -0.1700
Data Index: 5489091 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.2455. Min Act: -0.1700
Data Index: 4769775 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1517. Min Act: -0.1700
Data Index: 8427077 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1830. Min Act: -0.1700
Data Index: 6318464 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1830. Min Act: -0.1700
Data Index: 1033545 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1517. Min Act: -0.1700
Data Index: 8742322 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1517. Min Act: -0.1700
Data Index: 7191339 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1517. Min Act: -0.1700
Data Index: 3989181 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1205. Min Act: -0.1700
Data Index: 2977169 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1517. Min Act: -0.1700
Data Index: 6146339 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1205. Min Act: -0.1700
Data Index: 5387903 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1205. Min Act: -0.1700
Data Index: 5795800 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3393. Min Range: -4.3393
Max Act: 4.1205. Min Act: -0.1700
Data Index: 4805877 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19