Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.7632. Min Act: -0.1700
Data Index: 4494862 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.6695. Min Act: -0.1700
Data Index: 7991625 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.5757. Min Act: -0.1700
Data Index: 6318437 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.6070. Min Act: -0.1700
Data Index: 458658 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.6070. Min Act: -0.1700
Data Index: 8561735 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.5445. Min Act: -0.1700
Data Index: 6600151 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.5445. Min Act: -0.1700
Data Index: 3245449 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.5132. Min Act: -0.1700
Data Index: 2091917 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.5757. Min Act: -0.1700
Data Index: 294501 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4820. Min Act: -0.1700
Data Index: 4931490 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4820. Min Act: -0.1700
Data Index: 7739094 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4820. Min Act: -0.1700
Data Index: 1897347 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4195. Min Act: -0.1700
Data Index: 2087709 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4195. Min Act: -0.1700
Data Index: 8154386 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.4195. Min Act: -0.1700
Data Index: 7371992 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.3882. Min Act: -0.1700
Data Index: 5609152 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.3570. Min Act: -0.1700
Data Index: 8712494 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.3570. Min Act: -0.1700
Data Index: 111592 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.3882. Min Act: -0.1700
Data Index: 2979049 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7632. Min Range: -5.7632
Max Act: 5.3257. Min Act: -0.1700
Data Index: 7661465 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19