Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1486 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.8929. Min Act: -0.1700
Data Index: 144743 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.7992. Min Act: -0.1700
Data Index: 4016 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.7367. Min Act: -0.1700
Data Index: 144732 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.7367. Min Act: -0.1700
Data Index: 841170 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.7367. Min Act: -0.1700
Data Index: 8341806 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.7054. Min Act: -0.1700
Data Index: 671515 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.6742. Min Act: -0.1700
Data Index: 2173887 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1831263 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.6117. Min Act: -0.1700
Data Index: 5743848 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1798419 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.6117. Min Act: -0.1700
Data Index: 329674 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 2278735 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 6657860 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 6575719 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 5937778 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 8611475 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5492. Min Act: -0.1700
Data Index: 999979 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5804. Min Act: -0.1700
Data Index: 6193377 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5492. Min Act: -0.1700
Data Index: 283505 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8929. Min Range: -4.8929
Max Act: 4.5492. Min Act: -0.1700
Data Index: 2806240 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19