Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1017. Min Range: -6.1017
Max Act: 6.1017. Min Act: -0.1700
Data Index: 8095466 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1017. Min Range: -6.1017
Max Act: 6.0392. Min Act: -0.1700
Data Index: 2600936 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.9142. Min Act: -0.1700
Data Index: 696161 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8517. Min Act: -0.1700
Data Index: 1064191 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8517. Min Act: -0.1700
Data Index: 5756132 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8517. Min Act: -0.1700
Data Index: 5044553 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.8205. Min Act: -0.1700
Data Index: 1994959 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7892. Min Act: -0.1700
Data Index: 4384790 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7892. Min Act: -0.1700
Data Index: 6212706 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 2159146 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3918850 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 5509201 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3054016 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 3477158 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6397573 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7118300 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 6105531 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 7953692 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6955. Min Act: -0.1700
Data Index: 6492084 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1017. Min Range: -6.1017
Max Act: 5.6642. Min Act: -0.1700
Data Index: 2511697 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19