Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1969 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.4776. Min Act: -0.1700
Data Index: 1487328 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.2901. Min Act: -0.1700
Data Index: 6318033 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.1338. Min Act: -0.1700
Data Index: 1629 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.1026. Min Act: -0.1700
Data Index: 3659665 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.0401. Min Act: -0.1700
Data Index: 1199589 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9776. Min Act: -0.1700
Data Index: 5466402 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4776. Min Range: -6.4776
Max Act: 6.0401. Min Act: -0.1700
Data Index: 5423525 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9776. Min Act: -0.1700
Data Index: 2796614 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9776. Min Act: -0.1700
Data Index: 5431220 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9776. Min Act: -0.1700
Data Index: 3661745 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9463. Min Act: -0.1700
Data Index: 3350007 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9463. Min Act: -0.1700
Data Index: 5537273 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9463. Min Act: -0.1700
Data Index: 2771673 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.9151. Min Act: -0.1700
Data Index: 1421521 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.8213. Min Act: -0.1700
Data Index: 4975732 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.8213. Min Act: -0.1700
Data Index: 6510234 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.8213. Min Act: -0.1700
Data Index: 2025480 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.7588. Min Act: -0.1700
Data Index: 7856864 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.8213. Min Act: -0.1700
Data Index: 4972125 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4776. Min Range: -6.4776
Max Act: 5.7901. Min Act: -0.1700
Data Index: 5210973 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19