Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.5534. Min Act: -0.1700
Data Index: 7097976 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.3346. Min Act: -0.1700
Data Index: 1655621 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.2409. Min Act: -0.1700
Data Index: 3011895 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.2096. Min Act: -0.1700
Data Index: 6969598 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.1784. Min Act: -0.1700
Data Index: 6600656 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.1471. Min Act: -0.1700
Data Index: 89308 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.1471. Min Act: -0.1700
Data Index: 8759564 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.1471. Min Act: -0.1700
Data Index: 6137284 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.0846. Min Act: -0.1700
Data Index: 8597593 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.0846. Min Act: -0.1700
Data Index: 5246580 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.0846. Min Act: -0.1700
Data Index: 5668061 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.0534. Min Act: -0.1700
Data Index: 6973723 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5534. Min Range: -7.5534
Max Act: 7.0534. Min Act: -0.1700
Data Index: 7627354 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.9909. Min Act: -0.1700
Data Index: 498821 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.9596. Min Act: -0.1700
Data Index: 1655622 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.9596. Min Act: -0.1700
Data Index: 7618403 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.8971. Min Act: -0.1700
Data Index: 7317528 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.8971. Min Act: -0.1700
Data Index: 7653039 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.8971. Min Act: -0.1700
Data Index: 2164816 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5534. Min Range: -7.5534
Max Act: 6.8971. Min Act: -0.1700
Data Index: 1367367 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19