Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2157 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.8089. Min Act: -0.1700
Data Index: 7105632 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.7464. Min Act: -0.1700
Data Index: 4446606 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.7151. Min Act: -0.1700
Data Index: 7496870 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.6839. Min Act: -0.1700
Data Index: 2053981 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5016822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5901. Min Act: -0.1700
Data Index: 3722414 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5901. Min Act: -0.1700
Data Index: 3799353 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 4419753 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 7762311 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 1282578 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 7166606 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 7078579 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 5888197 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 2388605 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 582678 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 440714 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 2455689 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 6971978 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 6117927 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8089. Min Range: -4.8089
Max Act: 4.5276. Min Act: -0.1700
Data Index: 7618075 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19