Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 856 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1142. Min Range: -8.1142
Max Act: 8.1142. Min Act: -0.1700
Data Index: 6826007 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1142. Min Range: -8.1142
Max Act: 7.1454. Min Act: -0.1700
Data Index: 1864633 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1142. Min Range: -8.1142
Max Act: 7.0517. Min Act: -0.1700
Data Index: 136763 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1142. Min Range: -8.1142
Max Act: 7.0204. Min Act: -0.1700
Data Index: 5362526 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.9892. Min Act: -0.1700
Data Index: 3998033 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.9579. Min Act: -0.1700
Data Index: 4475081 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.8642. Min Act: -0.1700
Data Index: 2267086 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.9267. Min Act: -0.1700
Data Index: 797850 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7704. Min Act: -0.1700
Data Index: 7846438 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.9267. Min Act: -0.1700
Data Index: 2880379 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.8329. Min Act: -0.1700
Data Index: 3076433 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7704. Min Act: -0.1700
Data Index: 7375005 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7079. Min Act: -0.1700
Data Index: 2074827 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.8017. Min Act: -0.1700
Data Index: 6168670 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.8017. Min Act: -0.1700
Data Index: 3531091 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7704. Min Act: -0.1700
Data Index: 8044296 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7392. Min Act: -0.1700
Data Index: 5736282 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.8017. Min Act: -0.1700
Data Index: 1120154 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7392. Min Act: -0.1700
Data Index: 2265270 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1142. Min Range: -8.1142
Max Act: 6.7392. Min Act: -0.1700
Data Index: 5431758 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19