Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3763 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.5250. Min Act: -0.1700
Data Index: 4985911 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.4937. Min Act: -0.1700
Data Index: 8012924 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.4000. Min Act: -0.1700
Data Index: 4490578 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.3375. Min Act: -0.1700
Data Index: 1125088 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.1500. Min Act: -0.1700
Data Index: 1016039 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5250. Min Range: -6.5250
Max Act: 6.0250. Min Act: -0.1700
Data Index: 103643 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.9000. Min Act: -0.1700
Data Index: 8688111 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.8687. Min Act: -0.1700
Data Index: 3786935 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.8375. Min Act: -0.1700
Data Index: 1227972 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.7750. Min Act: -0.1700
Data Index: 1266176 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.7437. Min Act: -0.1700
Data Index: 6735667 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.7437. Min Act: -0.1700
Data Index: 2713068 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.6812. Min Act: -0.1700
Data Index: 1080415 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.7125. Min Act: -0.1700
Data Index: 5056337 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.6812. Min Act: -0.1700
Data Index: 1187194 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.6500. Min Act: -0.1700
Data Index: 7392460 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.6187. Min Act: -0.1700
Data Index: 8053939 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.5562. Min Act: -0.1700
Data Index: 1344044 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7341302 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5250. Min Range: -6.5250
Max Act: 5.5250. Min Act: -0.1700
Data Index: 1360980 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19