Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.2664. Min Act: -0.1700
Data Index: 1377918 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.0789. Min Act: -0.1700
Data Index: 5939068 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.0789. Min Act: -0.1700
Data Index: 4291360 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.9851. Min Act: -0.1700
Data Index: 6034988 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.0789. Min Act: -0.1700
Data Index: 2763051 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.0789. Min Act: -0.1700
Data Index: 4517983 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2664. Min Range: -7.2664
Max Act: 7.1414. Min Act: -0.1700
Data Index: 1386775 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.9539. Min Act: -0.1700
Data Index: 6906154 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8914. Min Act: -0.1700
Data Index: 6404902 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.9226. Min Act: -0.1700
Data Index: 1047867 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.9539. Min Act: -0.1700
Data Index: 8210360 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8289. Min Act: -0.1700
Data Index: 1556043 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8914. Min Act: -0.1700
Data Index: 4460178 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.7976. Min Act: -0.1700
Data Index: 8218701 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8914. Min Act: -0.1700
Data Index: 5640158 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8601. Min Act: -0.1700
Data Index: 2770711 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8289. Min Act: -0.1700
Data Index: 5913273 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8289. Min Act: -0.1700
Data Index: 4014274 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.8289. Min Act: -0.1700
Data Index: 2678824 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2664. Min Range: -7.2664
Max Act: 6.7664. Min Act: -0.1700
Data Index: 456844 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19