Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1665 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.9056. Min Act: -0.1700
Data Index: 2400880 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.8430. Min Act: -0.1700
Data Index: 5338548 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.7023. Min Act: -0.1700
Data Index: 5220452 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.6866. Min Act: -0.1700
Data Index: 2178574 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.6710. Min Act: -0.1700
Data Index: 5087441 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.6710. Min Act: -0.1700
Data Index: 6164630 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.6241. Min Act: -0.1700
Data Index: 203858 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5928. Min Act: -0.1700
Data Index: 4674311 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5928. Min Act: -0.1700
Data Index: 4826817 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5928. Min Act: -0.1700
Data Index: 6592194 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5301. Min Act: -0.1700
Data Index: 4957380 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5458. Min Act: -0.1700
Data Index: 3112145 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5458. Min Act: -0.1700
Data Index: 5831787 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5458. Min Act: -0.1700
Data Index: 5102678 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5145. Min Act: -0.1700
Data Index: 1821375 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5301. Min Act: -0.1700
Data Index: 5917782 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5301. Min Act: -0.1700
Data Index: 5633387 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5301. Min Act: -0.1700
Data Index: 901992 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.4988. Min Act: -0.1700
Data Index: 1445360 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9056. Min Range: -3.9056
Max Act: 3.5145. Min Act: -0.1700
Data Index: 5774925 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19