Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1320 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.6122. Min Act: -0.1700
Data Index: 1970147 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.5810. Min Act: -0.1700
Data Index: 7063837 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4872. Min Act: -0.1700
Data Index: 379650 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4872. Min Act: -0.1700
Data Index: 10218 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4560. Min Act: -0.1694
Data Index: 7351505 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4247. Min Act: -0.1700
Data Index: 5049018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4247. Min Act: -0.1700
Data Index: 4446480 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.4247. Min Act: -0.1700
Data Index: 7649845 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3934. Min Act: -0.1700
Data Index: 6783666 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3934. Min Act: -0.1700
Data Index: 2056177 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3934. Min Act: -0.1700
Data Index: 226985 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3934. Min Act: -0.1700
Data Index: 7865671 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 705660 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 1645926 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 4866755 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 6146777 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 7481332 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3622. Min Act: -0.1700
Data Index: 3174762 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3309. Min Act: -0.1700
Data Index: 4124521 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6122. Min Range: -4.6122
Max Act: 4.3309. Min Act: -0.1700
Data Index: 4640974 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19