Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1997 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.8337. Min Act: -0.1700
Data Index: 8780730 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2399. Min Act: -0.1700
Data Index: 8342962 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2399. Min Act: -0.1700
Data Index: 4624820 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2399. Min Act: -0.1700
Data Index: 4506700 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2399. Min Act: -0.1700
Data Index: 162795 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2087. Min Act: -0.1700
Data Index: 4695834 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1774. Min Act: -0.1700
Data Index: 3196630 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2087. Min Act: -0.1700
Data Index: 6718908 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1774. Min Act: -0.1700
Data Index: 6752866 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1774. Min Act: -0.1700
Data Index: 752470 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1774. Min Act: -0.1700
Data Index: 3816839 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1462. Min Act: -0.1700
Data Index: 8161343 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1462. Min Act: -0.1700
Data Index: 8255829 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1149. Min Act: -0.1700
Data Index: 1831309 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1149. Min Act: -0.1700
Data Index: 1989073 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.0836. Min Act: -0.1700
Data Index: 945853 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.1462. Min Act: -0.1700
Data Index: 881907 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.0524. Min Act: -0.1700
Data Index: 1114238 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.0836. Min Act: -0.1700
Data Index: 2563781 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.0836. Min Act: -0.1700
Data Index: 5078338 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19