Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.5812. Min Act: -0.1700
Data Index: 2899453 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.5500. Min Act: -0.1700
Data Index: 2971089 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.3937. Min Act: -0.1700
Data Index: 266865 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.2375. Min Act: -0.1700
Data Index: 5515452 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.2062. Min Act: -0.1700
Data Index: 1037920 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.2062. Min Act: -0.1700
Data Index: 3032369 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.1437. Min Act: -0.1700
Data Index: 8039107 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.1437. Min Act: -0.1700
Data Index: 5582148 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4926906 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 3567967 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8073588 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 3083520 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 1474594 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0500. Min Act: -0.1700
Data Index: 96966 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0500. Min Act: -0.1700
Data Index: 7551136 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0187. Min Act: -0.1700
Data Index: 6261260 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0187. Min Act: -0.1700
Data Index: 1561530 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8799162 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0187. Min Act: -0.1700
Data Index: 2406879 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5812. Min Range: -6.5812
Max Act: 6.0187. Min Act: -0.1700
Data Index: 6555005 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19