Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4668 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.5203. Min Act: -0.1700
Data Index: 4985786 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4578. Min Act: -0.1700
Data Index: 6290324 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4578. Min Act: -0.1700
Data Index: 1214752 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4266. Min Act: -0.1700
Data Index: 506334 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4266. Min Act: -0.1700
Data Index: 506331 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4266. Min Act: -0.1700
Data Index: 506341 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3953. Min Act: -0.1700
Data Index: 5032985 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3953. Min Act: -0.1700
Data Index: 506326 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.4266. Min Act: -0.1700
Data Index: 4812265 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3953. Min Act: -0.1700
Data Index: 7512155 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3953. Min Act: -0.1700
Data Index: 758283 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 2021964 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 506343 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 3425360 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 506337 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 506339 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3641. Min Act: -0.1700
Data Index: 290157 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3328. Min Act: -0.1700
Data Index: 506332 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3328. Min Act: -0.1700
Data Index: 506333 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5203. Min Range: -4.5203
Max Act: 4.3328. Min Act: -0.1700
Data Index: 506340 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19