Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4123 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4081. Min Range: -7.4081
Max Act: 7.4081. Min Act: -0.1700
Data Index: 2123373 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.7519. Min Act: -0.1700
Data Index: 5724916 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.7519. Min Act: -0.1700
Data Index: 2897559 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6894. Min Act: -0.1700
Data Index: 4872530 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 7498260 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6581. Min Act: -0.1700
Data Index: 2070189 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 7378768 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 6034318 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.6269. Min Act: -0.1700
Data Index: 349523 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5956. Min Act: -0.1700
Data Index: 8541175 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5956. Min Act: -0.1700
Data Index: 5286908 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5956. Min Act: -0.1700
Data Index: 1240885 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5644. Min Act: -0.1700
Data Index: 2869941 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5331. Min Act: -0.1700
Data Index: 7121026 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.5019. Min Act: -0.1700
Data Index: 2872156 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.4706. Min Act: -0.1700
Data Index: 5576199 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.4394. Min Act: -0.1700
Data Index: 1127932 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.4081. Min Act: -0.1700
Data Index: 3357498 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.4394. Min Act: -0.1700
Data Index: 4690305 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4081. Min Range: -7.4081
Max Act: 6.4081. Min Act: -0.1700
Data Index: 3309088 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19