Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.4100. Min Act: -0.1700
Data Index: 4344839 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.2225. Min Act: -0.1700
Data Index: 8012949 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 91552 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 404895 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 3019149 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 1938057 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 6979257 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 6735789 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 1090081 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 3326181 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 1507672 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0975. Min Act: -0.1700
Data Index: 8021352 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.1600. Min Act: -0.1700
Data Index: 7561081 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4100. Min Range: -10.4100
Max Act: 9.9725. Min Act: -0.1700
Data Index: 3761809 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 3956680 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 6915920 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4100. Min Range: -10.4100
Max Act: 9.9725. Min Act: -0.1700
Data Index: 2561736 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 1277017 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 5753764 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4100. Min Range: -10.4100
Max Act: 10.0350. Min Act: -0.1700
Data Index: 6636252 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19