Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3777 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.5187. Min Act: -0.1700
Data Index: 1414402 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4250. Min Act: -0.1700
Data Index: 8357664 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6150624 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 8507067 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7394812 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1750. Min Act: -0.1700
Data Index: 5592761 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1125. Min Act: -0.1700
Data Index: 4909631 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 1068649 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 5389195 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0500. Min Act: -0.1700
Data Index: 5817534 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0812. Min Act: -0.1700
Data Index: 7093756 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0500. Min Act: -0.1700
Data Index: 2184318 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 5417972 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 4206714 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 7323275 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 1169334 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 8141579 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9875. Min Act: -0.1700
Data Index: 1089999 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9875. Min Act: -0.1700
Data Index: 6737893 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5187. Min Range: -5.5187
Max Act: 4.9875. Min Act: -0.1700
Data Index: 7637502 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19