Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.4188. Min Act: -0.1700
Data Index: 6914869 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.3563. Min Act: -0.1700
Data Index: 6240648 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.2626. Min Act: -0.1700
Data Index: 768979 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.2626. Min Act: -0.1700
Data Index: 3876211 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.1376. Min Act: -0.1700
Data Index: 6721874 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.1376. Min Act: -0.1700
Data Index: 6935193 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.1063. Min Act: -0.1700
Data Index: 6295706 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.0751. Min Act: -0.1700
Data Index: 5501538 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.1063. Min Act: -0.1700
Data Index: 2716726 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4188. Min Range: -7.4188
Max Act: 7.0438. Min Act: -0.1700
Data Index: 5625092 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.9188. Min Act: -0.1700
Data Index: 5292754 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.9188. Min Act: -0.1700
Data Index: 1931246 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.9188. Min Act: -0.1700
Data Index: 2299976 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8563. Min Act: -0.1700
Data Index: 8382322 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8876. Min Act: -0.1700
Data Index: 8320301 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8563. Min Act: -0.1700
Data Index: 5459452 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8563. Min Act: -0.1700
Data Index: 1761518 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8251. Min Act: -0.1700
Data Index: 3738855 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8251. Min Act: -0.1700
Data Index: 1918423 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4188. Min Range: -7.4188
Max Act: 6.8251. Min Act: -0.1700
Data Index: 8082097 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19