Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.1141. Min Act: -0.1700
Data Index: 1501664 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.0829. Min Act: -0.1700
Data Index: 5779536 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.0516. Min Act: -0.1700
Data Index: 1862121 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.0516. Min Act: -0.1700
Data Index: 2917750 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.0516. Min Act: -0.1700
Data Index: 5779946 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1141. Min Range: -5.1141
Max Act: 5.0204. Min Act: -0.1700
Data Index: 8589002 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.9579. Min Act: -0.1700
Data Index: 4022797 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1045111 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.9266. Min Act: -0.1700
Data Index: 6007881 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.9266. Min Act: -0.1700
Data Index: 223399 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8641. Min Act: -0.1700
Data Index: 4428225 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8954. Min Act: -0.1700
Data Index: 6462859 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8954. Min Act: -0.1700
Data Index: 2926030 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8954. Min Act: -0.1700
Data Index: 2327607 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8954. Min Act: -0.1700
Data Index: 976260 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8641. Min Act: -0.1700
Data Index: 2296642 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8641. Min Act: -0.1700
Data Index: 3711582 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7673898 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8641. Min Act: -0.1700
Data Index: 7200804 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1141. Min Range: -5.1141
Max Act: 4.8329. Min Act: -0.1700
Data Index: 3322367 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19