Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4268 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1430. Min Range: -7.1430
Max Act: 7.1430. Min Act: -0.1700
Data Index: 1035533 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.8930. Min Act: -0.1700
Data Index: 8452082 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.8305. Min Act: -0.1700
Data Index: 8665384 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.7993. Min Act: -0.1700
Data Index: 3412338 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.7993. Min Act: -0.1700
Data Index: 7757910 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.6743. Min Act: -0.1700
Data Index: 6053882 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.6430. Min Act: -0.1700
Data Index: 6921950 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.6430. Min Act: -0.1700
Data Index: 8067079 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.6118. Min Act: -0.1700
Data Index: 3660849 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.5805. Min Act: -0.1700
Data Index: 8721027 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.6118. Min Act: -0.1700
Data Index: 1297863 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.5180. Min Act: -0.1700
Data Index: 7680563 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.5493. Min Act: -0.1700
Data Index: 4487937 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 2014549 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.5493. Min Act: -0.1700
Data Index: 1128148 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 367522 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 5580108 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 6911092 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 1476233 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1430. Min Range: -7.1430
Max Act: 6.4868. Min Act: -0.1700
Data Index: 7242805 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19