Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.4005. Min Act: -0.1700
Data Index: 724150 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.3693. Min Act: -0.1700
Data Index: 261932 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.3068. Min Act: -0.1700
Data Index: 7022925 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.3068. Min Act: -0.1700
Data Index: 697207 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7945717 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.2755. Min Act: -0.1700
Data Index: 8290934 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.3068. Min Act: -0.1700
Data Index: 1576265 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.2130. Min Act: -0.1700
Data Index: 4742997 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7782545 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.2443. Min Act: -0.1700
Data Index: 3305633 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1818. Min Act: -0.1700
Data Index: 1883339 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1818. Min Act: -0.1700
Data Index: 5728738 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1818. Min Act: -0.1700
Data Index: 1524324 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1505. Min Act: -0.1700
Data Index: 8800966 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1505. Min Act: -0.1700
Data Index: 9728 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5413700 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5157398 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.0880. Min Act: -0.1700
Data Index: 3137486 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.0255. Min Act: -0.1700
Data Index: 1812550 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4005. Min Range: -5.4005
Max Act: 5.0568. Min Act: -0.1700
Data Index: 6152300 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19