Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2309 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2581. Min Range: -7.2581
Max Act: 7.2581. Min Act: -0.1700
Data Index: 1040131 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.9143. Min Act: -0.1700
Data Index: 6709553 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.8518. Min Act: -0.1700
Data Index: 3952913 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.7893. Min Act: -0.1700
Data Index: 6869893 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.7893. Min Act: -0.1700
Data Index: 2620248 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.7268. Min Act: -0.1700
Data Index: 4294432 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6877061 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6956. Min Act: -0.1700
Data Index: 7927832 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6331. Min Act: -0.1700
Data Index: 3612804 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6331. Min Act: -0.1700
Data Index: 6485676 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6018. Min Act: -0.1700
Data Index: 3350909 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6018. Min Act: -0.1700
Data Index: 6911218 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.6018. Min Act: -0.1700
Data Index: 5804949 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5393. Min Act: -0.1700
Data Index: 225812 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5081. Min Act: -0.1700
Data Index: 405401 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5393. Min Act: -0.1700
Data Index: 427484 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5081. Min Act: -0.1700
Data Index: 7872140 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5393. Min Act: -0.1700
Data Index: 8104396 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5081. Min Act: -0.1700
Data Index: 5274182 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2581. Min Range: -7.2581
Max Act: 6.5081. Min Act: -0.1700
Data Index: 7581916 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19