Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0689. Min Range: -4.0689
Max Act: 4.0689. Min Act: -0.1700
Data Index: 7894768 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0689. Min Range: -4.0689
Max Act: 4.0063. Min Act: -0.1700
Data Index: 3623880 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.9438. Min Act: -0.1700
Data Index: 5821201 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.8188. Min Act: -0.1700
Data Index: 6136577 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.8188. Min Act: -0.1700
Data Index: 2157037 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7875. Min Act: -0.1700
Data Index: 6071822 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7875. Min Act: -0.1700
Data Index: 2527520 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7875. Min Act: -0.1700
Data Index: 3391800 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7562. Min Act: -0.1700
Data Index: 8291627 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7562. Min Act: -0.1700
Data Index: 7574177 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7562. Min Act: -0.1700
Data Index: 289663 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 5589860 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 604090 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 50869 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 7931945 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 563345 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7562. Min Act: -0.1700
Data Index: 4976939 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 2997340 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.7249. Min Act: -0.1700
Data Index: 6102123 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0689. Min Range: -4.0689
Max Act: 3.6936. Min Act: -0.1700
Data Index: 6829074 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19