Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.1178. Min Act: -0.1700
Data Index: 8672137 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.1002. Min Act: -0.1700
Data Index: 5778429 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0915. Min Act: -0.1700
Data Index: 3818805 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0827. Min Act: -0.1700
Data Index: 5207495 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0740. Min Act: -0.1700
Data Index: 392530 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0565. Min Act: -0.1700
Data Index: 6661873 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0652. Min Act: -0.1700
Data Index: 6257573 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0740. Min Act: -0.1700
Data Index: 8696113 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0478. Min Act: -0.1700
Data Index: 4099330 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0652. Min Act: -0.1700
Data Index: 5002545 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0478. Min Act: -0.1700
Data Index: 6175070 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0478. Min Act: -0.1700
Data Index: 878027 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0304. Min Act: -0.1700
Data Index: 3809124 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0391. Min Act: -0.1700
Data Index: 2036016 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0304. Min Act: -0.1700
Data Index: 5226611 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0304. Min Act: -0.1700
Data Index: 7528250 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0304. Min Act: -0.1700
Data Index: 1774931 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0304. Min Act: -0.1700
Data Index: 5452560 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0217. Min Act: -0.1700
Data Index: 5480584 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1178. Min Range: -1.1178
Max Act: 1.0217. Min Act: -0.1700
Data Index: 6273957 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19