Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2267. Min Act: -0.1700
Data Index: 2596602 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2267. Min Act: -0.1700
Data Index: 928135 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2102. Min Act: -0.1700
Data Index: 619880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.2102. Min Act: -0.1700
Data Index: 4087559 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1936. Min Act: -0.1700
Data Index: 5116391 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1770. Min Act: -0.1700
Data Index: 3566835 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1770. Min Act: -0.1700
Data Index: 7456495 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1603. Min Act: -0.1700
Data Index: 4087560 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1770. Min Act: -0.1700
Data Index: 4087565 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1270. Min Act: -0.1700
Data Index: 4087564 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0935. Min Act: -0.1700
Data Index: 3182959 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1102. Min Act: -0.1700
Data Index: 3487289 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1102. Min Act: -0.1700
Data Index: 127631 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1102. Min Act: -0.1700
Data Index: 8767641 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.1102. Min Act: -0.1700
Data Index: 4045923 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0935. Min Act: -0.1700
Data Index: 8159967 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0935. Min Act: -0.1700
Data Index: 6469974 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0935. Min Act: -0.1700
Data Index: 6036273 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0767. Min Act: -0.1700
Data Index: 7394538 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2267. Min Range: -2.2267
Max Act: 2.0767. Min Act: -0.1700
Data Index: 1084789 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19