Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1281. Min Range: -8.1281
Max Act: 8.1281. Min Act: -0.1700
Data Index: 8335856 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1281. Min Range: -8.1281
Max Act: 8.0031. Min Act: -0.1700
Data Index: 8335858 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.9406. Min Act: -0.1700
Data Index: 8335860 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.8781. Min Act: -0.1700
Data Index: 8335861 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.9406. Min Act: -0.1700
Data Index: 8335864 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.7531. Min Act: -0.1700
Data Index: 1203849 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.8156. Min Act: -0.1700
Data Index: 8335859 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.7531. Min Act: -0.1700
Data Index: 6814480 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.6906. Min Act: -0.1700
Data Index: 2812631 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.6906. Min Act: -0.1700
Data Index: 8335863 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.7531. Min Act: -0.1700
Data Index: 6197264 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5968. Min Act: -0.1700
Data Index: 8335862 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5343. Min Act: -0.1700
Data Index: 5678902 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5343. Min Act: -0.1700
Data Index: 8335857 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5343. Min Act: -0.1700
Data Index: 783403 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5031. Min Act: -0.1700
Data Index: 667151 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.5031. Min Act: -0.1700
Data Index: 6276753 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.4718. Min Act: -0.1700
Data Index: 7465533 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.4406. Min Act: -0.1700
Data Index: 2584770 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1281. Min Range: -8.1281
Max Act: 7.4093. Min Act: -0.1700
Data Index: 4987022 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19