Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.3890. Min Act: -0.1700
Data Index: 7544225 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.3265. Min Act: -0.1700
Data Index: 1220932 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.2640. Min Act: -0.1700
Data Index: 2557479 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.2640. Min Act: -0.1700
Data Index: 8495128 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.2640. Min Act: -0.1700
Data Index: 5727321 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.2328. Min Act: -0.1700
Data Index: 6795688 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.2328. Min Act: -0.1700
Data Index: 7743103 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1703. Min Act: -0.1700
Data Index: 6239941 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1703. Min Act: -0.1700
Data Index: 3723666 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7221329 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1437643 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1390. Min Act: -0.1700
Data Index: 3900866 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1078. Min Act: -0.1700
Data Index: 2697566 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1390. Min Act: -0.1700
Data Index: 7728603 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1078. Min Act: -0.1700
Data Index: 1589028 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1078. Min Act: -0.1700
Data Index: 4736569 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.1078. Min Act: -0.1700
Data Index: 6848003 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.0765. Min Act: -0.1700
Data Index: 3126404 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.0765. Min Act: -0.1700
Data Index: 251279 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3890. Min Range: -6.3890
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5697760 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19