Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0327. Min Range: -6.0327
Max Act: 6.0327. Min Act: -0.1700
Data Index: 6415327 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0327. Min Range: -6.0327
Max Act: 6.0015. Min Act: -0.1700
Data Index: 3973727 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.9390. Min Act: -0.1700
Data Index: 7658307 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.8765. Min Act: -0.1700
Data Index: 677772 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.8140. Min Act: -0.1700
Data Index: 1929923 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.8140. Min Act: -0.1700
Data Index: 6166874 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.8140. Min Act: -0.1700
Data Index: 8461303 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7827. Min Act: -0.1700
Data Index: 3879905 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7515. Min Act: -0.1700
Data Index: 7758074 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7515. Min Act: -0.1700
Data Index: 3888788 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7515. Min Act: -0.1700
Data Index: 1378907 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7202. Min Act: -0.1700
Data Index: 7784509 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7202. Min Act: -0.1700
Data Index: 5386592 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7515. Min Act: -0.1700
Data Index: 3047614 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.7202. Min Act: -0.1700
Data Index: 4419345 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.6890. Min Act: -0.1700
Data Index: 3381633 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.6890. Min Act: -0.1700
Data Index: 4706354 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.6890. Min Act: -0.1700
Data Index: 6816125 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.6265. Min Act: -0.1700
Data Index: 3460673 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0327. Min Range: -6.0327
Max Act: 5.6265. Min Act: -0.1700
Data Index: 6333065 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19