Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.6630. Min Act: -0.1700
Data Index: 4626774 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.5067. Min Act: -0.1700
Data Index: 6795437 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.4130. Min Act: -0.1700
Data Index: 1298576 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.4130. Min Act: -0.1700
Data Index: 5691569 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.3817. Min Act: -0.1700
Data Index: 8038128 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.4130. Min Act: -0.1700
Data Index: 8539032 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.3817. Min Act: -0.1700
Data Index: 4605008 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.4130. Min Act: -0.1700
Data Index: 2849122 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.4130. Min Act: -0.1700
Data Index: 7878057 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.3192. Min Act: -0.1700
Data Index: 7584281 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1942. Min Act: -0.1700
Data Index: 3559499 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.2255. Min Act: -0.1700
Data Index: 8560610 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1942. Min Act: -0.1700
Data Index: 4466697 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1942. Min Act: -0.1700
Data Index: 1749452 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1942. Min Act: -0.1700
Data Index: 624064 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1942. Min Act: -0.1700
Data Index: 4992980 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 4813672 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 5796911 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 3907357 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6630. Min Range: -6.6630
Max Act: 6.1630. Min Act: -0.1700
Data Index: 4758603 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19