Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.5027. Min Act: -0.1700
Data Index: 2508236 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.5027. Min Act: -0.1700
Data Index: 4345770 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.3777. Min Act: -0.1700
Data Index: 6924300 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.3777. Min Act: -0.1700
Data Index: 5011879 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.2527. Min Act: -0.1700
Data Index: 865835 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.1902. Min Act: -0.1700
Data Index: 3683737 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.1902. Min Act: -0.1700
Data Index: 1114518 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.1277. Min Act: -0.1700
Data Index: 4299017 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.1277. Min Act: -0.1700
Data Index: 1066707 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.1277. Min Act: -0.1700
Data Index: 3349202 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.0027. Min Act: -0.1700
Data Index: 8583271 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5027. Min Range: -8.5027
Max Act: 8.0027. Min Act: -0.1700
Data Index: 567795 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.9402. Min Act: -0.1700
Data Index: 7675916 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.9402. Min Act: -0.1700
Data Index: 7197172 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.8777. Min Act: -0.1700
Data Index: 7751957 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.8152. Min Act: -0.1700
Data Index: 6280949 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.8777. Min Act: -0.1700
Data Index: 1821830 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.8152. Min Act: -0.1700
Data Index: 215155 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.8152. Min Act: -0.1700
Data Index: 2070215 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5027. Min Range: -8.5027
Max Act: 7.7527. Min Act: -0.1700
Data Index: 669260 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19