Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.8081. Min Act: -0.1700
Data Index: 6108090 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.3706. Min Act: -0.1700
Data Index: 3828580 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.3081. Min Act: -0.1700
Data Index: 311438 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.2769. Min Act: -0.1700
Data Index: 3209272 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.2144. Min Act: -0.1700
Data Index: 3083187 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 5498073 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 4812270 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 5006777 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 7379149 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 1876963 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 1043506 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 786997 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 6850836 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0894. Min Act: -0.1700
Data Index: 1908557 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0894. Min Act: -0.1700
Data Index: 3991338 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6928284 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6275764 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 5929979 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 418337 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8081. Min Range: -6.8081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 4156688 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19