Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2213 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2062. Min Range: -7.2062
Max Act: 7.2062. Min Act: -0.1700
Data Index: 7149101 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2062. Min Range: -7.2062
Max Act: 7.2062. Min Act: -0.1700
Data Index: 5802126 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2062. Min Range: -7.2062
Max Act: 7.0500. Min Act: -0.1700
Data Index: 2656533 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.9875. Min Act: -0.1700
Data Index: 6334609 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8937. Min Act: -0.1700
Data Index: 3234692 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.9250. Min Act: -0.1700
Data Index: 7042400 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8625. Min Act: -0.1700
Data Index: 4750846 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8625. Min Act: -0.1700
Data Index: 6233194 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2197218 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.8000. Min Act: -0.1700
Data Index: 1647848 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.7687. Min Act: -0.1700
Data Index: 6441528 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 470030 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6750. Min Act: -0.1700
Data Index: 1050976 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 6797863 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7476550 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.5812. Min Act: -0.1700
Data Index: 5421767 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6437. Min Act: -0.1700
Data Index: 5584837 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6125. Min Act: -0.1700
Data Index: 1032175 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.5812. Min Act: -0.1700
Data Index: 6019614 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2062. Min Range: -7.2062
Max Act: 6.6125. Min Act: -0.1700
Data Index: 5203234 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19