Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.4731. Min Act: -0.1700
Data Index: 296470 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.4731. Min Act: -0.1700
Data Index: 2782858 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.4106. Min Act: -0.1700
Data Index: 1848285 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.3481. Min Act: -0.1700
Data Index: 8367571 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7268903 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.2231. Min Act: -0.1700
Data Index: 4988667 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.2231. Min Act: -0.1700
Data Index: 2274652 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.2543. Min Act: -0.1700
Data Index: 2170293 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.2231. Min Act: -0.1700
Data Index: 6759959 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1918. Min Act: -0.1700
Data Index: 8485953 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1606. Min Act: -0.1700
Data Index: 2466797 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1918. Min Act: -0.1700
Data Index: 4704115 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1918. Min Act: -0.1700
Data Index: 3072712 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1606. Min Act: -0.1700
Data Index: 8101590 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1606. Min Act: -0.1700
Data Index: 7845476 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1606. Min Act: -0.1700
Data Index: 616994 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5121708 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.0981. Min Act: -0.1700
Data Index: 4380583 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.0981. Min Act: -0.1700
Data Index: 6751222 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4731. Min Range: -6.4731
Max Act: 6.1293. Min Act: -0.1700
Data Index: 5095079 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19